Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4670 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.6271. Min Act: -0.1700
Data Index: 1458785 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.6271. Min Act: -0.1700
Data Index: 4614268 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.4083. Min Act: -0.1700
Data Index: 1315197 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.3771. Min Act: -0.1700
Data Index: 8603904 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.3146. Min Act: -0.1700
Data Index: 5870895 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.2833. Min Act: -0.1700
Data Index: 2842877 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.1583. Min Act: -0.1700
Data Index: 4143728 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.1271. Min Act: -0.1700
Data Index: 1698688 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.1271. Min Act: -0.1700
Data Index: 1177351 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3462316 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.0021. Min Act: -0.1700
Data Index: 14490 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.0021. Min Act: -0.1700
Data Index: 5733572 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6271. Min Range: -5.6271
Max Act: 5.0021. Min Act: -0.1700
Data Index: 5576766 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6271. Min Range: -5.6271
Max Act: 4.9396. Min Act: -0.1700
Data Index: 4450949 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6271. Min Range: -5.6271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 1985412 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6271. Min Range: -5.6271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 519603 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6271. Min Range: -5.6271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 6993285 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6271. Min Range: -5.6271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 5304831 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6271. Min Range: -5.6271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 4666660 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6271. Min Range: -5.6271
Max Act: 4.9708. Min Act: -0.1700
Data Index: 2244996 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19