Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4957 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.7176. Min Act: -0.1700
Data Index: 6655231 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.7489. Min Act: -0.1700
Data Index: 416702 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.7176. Min Act: -0.1700
Data Index: 7678178 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6864. Min Act: -0.1700
Data Index: 637749 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6864. Min Act: -0.1700
Data Index: 1087126 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6551. Min Act: -0.1700
Data Index: 7677565 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6864. Min Act: -0.1700
Data Index: 2223072 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6551. Min Act: -0.1700
Data Index: 4077644 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6551. Min Act: -0.1700
Data Index: 3780418 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6551. Min Act: -0.1700
Data Index: 4397940 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6551. Min Act: -0.1700
Data Index: 3188790 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6551. Min Act: -0.1700
Data Index: 5498536 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6239. Min Act: -0.1700
Data Index: 7596391 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6551. Min Act: -0.1700
Data Index: 7466477 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6239. Min Act: -0.1700
Data Index: 61949 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6239. Min Act: -0.1700
Data Index: 5650512 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6551. Min Act: -0.1700
Data Index: 5513256 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6239. Min Act: -0.1700
Data Index: 8166690 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6239. Min Act: -0.1700
Data Index: 4301861 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7489. Min Range: -4.7489
Max Act: 4.6239. Min Act: -0.1700
Data Index: 6160800 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19