Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4664 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.3420. Min Range: -11.3420
Max Act: 11.3420. Min Act: -0.1700
Data Index: 5233728 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3420. Min Range: -11.3420
Max Act: 11.1545. Min Act: -0.1700
Data Index: 5233725 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3420. Min Range: -11.3420
Max Act: 11.0295. Min Act: -0.1700
Data Index: 2229220 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.9670. Min Act: -0.1700
Data Index: 7000908 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.9670. Min Act: -0.1700
Data Index: 4945243 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.8420. Min Act: -0.1700
Data Index: 6135423 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.8420. Min Act: -0.1700
Data Index: 3019999 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.8420. Min Act: -0.1700
Data Index: 7466430 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.7795. Min Act: -0.1700
Data Index: 3884839 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.7170. Min Act: -0.1700
Data Index: 3761917 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.6545. Min Act: -0.1700
Data Index: 5657956 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.6545. Min Act: -0.1700
Data Index: 4919635 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.5920. Min Act: -0.1700
Data Index: 4266847 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.5920. Min Act: -0.1700
Data Index: 2896925 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.5920. Min Act: -0.1700
Data Index: 3761908 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.5920. Min Act: -0.1700
Data Index: 8803184 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.5295. Min Act: -0.1700
Data Index: 2655354 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.5295. Min Act: -0.1700
Data Index: 8256155 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.5920. Min Act: -0.1700
Data Index: 3105246 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3420. Min Range: -11.3420
Max Act: 10.5295. Min Act: -0.1700
Data Index: 6684480 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19