Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.8364. Min Act: -0.1700
Data Index: 7296536 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.7739. Min Act: -0.1700
Data Index: 1677377 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.7114. Min Act: -0.1700
Data Index: 7066466 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.6489. Min Act: -0.1700
Data Index: 6534556 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.6176. Min Act: -0.1700
Data Index: 629316 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.6176. Min Act: -0.1700
Data Index: 2887994 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.6176. Min Act: -0.1700
Data Index: 2096545 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.5551. Min Act: -0.1700
Data Index: 7865367 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4926. Min Act: -0.1700
Data Index: 2932202 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4926. Min Act: -0.1700
Data Index: 7327161 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4614. Min Act: -0.1700
Data Index: 5245137 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4301. Min Act: -0.1700
Data Index: 1191044 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4614. Min Act: -0.1700
Data Index: 6186765 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.3989. Min Act: -0.1700
Data Index: 8358531 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4301. Min Act: -0.1700
Data Index: 3301007 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4301. Min Act: -0.1700
Data Index: 6125819 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4301. Min Act: -0.1700
Data Index: 5776039 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4301. Min Act: -0.1700
Data Index: 3661627 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.4301. Min Act: -0.1700
Data Index: 3924527 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8364. Min Range: -6.8364
Max Act: 6.3989. Min Act: -0.1700
Data Index: 621744 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19