Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4497 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.4380. Min Act: -0.1700
Data Index: 7736045 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.2818. Min Act: -0.1700
Data Index: 2398211 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.1255. Min Act: -0.1700
Data Index: 1270451 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.1255. Min Act: -0.1700
Data Index: 3443387 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.0943. Min Act: -0.1700
Data Index: 8153029 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.0630. Min Act: -0.1700
Data Index: 6475753 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.0318. Min Act: -0.1700
Data Index: 3511318 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.0318. Min Act: -0.1700
Data Index: 8216967 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.0318. Min Act: -0.1700
Data Index: 3561785 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.0318. Min Act: -0.1700
Data Index: 4993242 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.0005. Min Act: -0.1700
Data Index: 7264711 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4380. Min Range: -6.4380
Max Act: 6.0005. Min Act: -0.1700
Data Index: 7582241 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4380. Min Range: -6.4380
Max Act: 5.9693. Min Act: -0.1700
Data Index: 2812884 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4380. Min Range: -6.4380
Max Act: 5.9693. Min Act: -0.1700
Data Index: 3999898 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4380. Min Range: -6.4380
Max Act: 5.9380. Min Act: -0.1699
Data Index: 6117547 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4380. Min Range: -6.4380
Max Act: 5.9380. Min Act: -0.1699
Data Index: 7810819 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4380. Min Range: -6.4380
Max Act: 5.9380. Min Act: -0.1700
Data Index: 6706182 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4380. Min Range: -6.4380
Max Act: 5.9380. Min Act: -0.1700
Data Index: 1095140 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4380. Min Range: -6.4380
Max Act: 5.9068. Min Act: -0.1700
Data Index: 5332155 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4380. Min Range: -6.4380
Max Act: 5.8755. Min Act: -0.1700
Data Index: 713300 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19