Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.8838. Min Act: -0.1700
Data Index: 628236 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.8526. Min Act: -0.1700
Data Index: 5384350 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.8213. Min Act: -0.1700
Data Index: 4829573 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.8213. Min Act: -0.1700
Data Index: 6966440 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7900. Min Act: -0.1700
Data Index: 8548701 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7900. Min Act: -0.1700
Data Index: 7091843 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7900. Min Act: -0.1700
Data Index: 8592423 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7900. Min Act: -0.1700
Data Index: 1840536 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7900. Min Act: -0.1700
Data Index: 987810 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7900. Min Act: -0.1700
Data Index: 5079188 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7900. Min Act: -0.1700
Data Index: 2006237 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7587. Min Act: -0.1700
Data Index: 7906993 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7587. Min Act: -0.1700
Data Index: 1682769 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7587. Min Act: -0.1700
Data Index: 1962749 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7587. Min Act: -0.1700
Data Index: 6886050 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7587. Min Act: -0.1700
Data Index: 6466308 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7275. Min Act: -0.1700
Data Index: 8049727 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.6962. Min Act: -0.1700
Data Index: 648417 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7275. Min Act: -0.1700
Data Index: 1708285 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8838. Min Range: -3.8838
Max Act: 3.7275. Min Act: -0.1700
Data Index: 34926 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19