Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.8154. Min Act: -0.1700
Data Index: 7188674 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.7529. Min Act: -0.1700
Data Index: 2700939 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.3779. Min Act: -0.1700
Data Index: 1690703 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.3779. Min Act: -0.1700
Data Index: 2607574 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.3154. Min Act: -0.1700
Data Index: 909647 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.3154. Min Act: -0.1700
Data Index: 859100 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.3154. Min Act: -0.1700
Data Index: 5724551 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2842. Min Act: -0.1700
Data Index: 6467812 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2842. Min Act: -0.1700
Data Index: 3337557 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2842. Min Act: -0.1700
Data Index: 7047042 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2529. Min Act: -0.1700
Data Index: 7906361 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.3154. Min Act: -0.1700
Data Index: 115363 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2529. Min Act: -0.1700
Data Index: 5659506 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2529. Min Act: -0.1700
Data Index: 7482442 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2529. Min Act: -0.1700
Data Index: 7606891 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2529. Min Act: -0.1700
Data Index: 5840572 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2217. Min Act: -0.1700
Data Index: 1827027 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2217. Min Act: -0.1700
Data Index: 7071009 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.2217. Min Act: -0.1700
Data Index: 2747885 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8154. Min Range: -5.8154
Max Act: 5.1904. Min Act: -0.1700
Data Index: 2148597 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19