Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1502 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.7176. Min Range: -9.7176
Max Act: 9.7176. Min Act: -0.1700
Data Index: 5227912 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7176. Min Range: -9.7176
Max Act: 9.2176. Min Act: -0.1700
Data Index: 4088165 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.9676. Min Act: -0.1700
Data Index: 1781741 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7176. Min Range: -9.7176
Max Act: 9.0301. Min Act: -0.1700
Data Index: 7313599 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7176. Min Range: -9.7176
Max Act: 9.0301. Min Act: -0.1700
Data Index: 13248 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.8426. Min Act: -0.1700
Data Index: 7312987 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.8426. Min Act: -0.1700
Data Index: 2686461 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.7801. Min Act: -0.1700
Data Index: 112392 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.9676. Min Act: -0.1700
Data Index: 917512 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.7801. Min Act: -0.1700
Data Index: 4482919 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.7801. Min Act: -0.1700
Data Index: 2686452 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.7801. Min Act: -0.1700
Data Index: 7098697 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.7176. Min Act: -0.1700
Data Index: 4494430 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.7176. Min Act: -0.1700
Data Index: 4496985 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.7176. Min Act: -0.1700
Data Index: 4557420 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.6551. Min Act: -0.1700
Data Index: 8825992 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.6551. Min Act: -0.1700
Data Index: 2739754 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.6551. Min Act: -0.1700
Data Index: 4131451 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.6551. Min Act: -0.1700
Data Index: 5232797 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7176. Min Range: -9.7176
Max Act: 8.5926. Min Act: -0.1700
Data Index: 5513935 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19