Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6285 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.5216. Min Act: -0.1700
Data Index: 3278775 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.4279. Min Act: -0.1700
Data Index: 5807145 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.3341. Min Act: -0.1700
Data Index: 6713568 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.2716. Min Act: -0.1700
Data Index: 7291198 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.2091. Min Act: -0.1700
Data Index: 5678530 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.1779. Min Act: -0.1700
Data Index: 8819799 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.1466. Min Act: -0.1700
Data Index: 5858027 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.1466. Min Act: -0.1700
Data Index: 6192852 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.1466. Min Act: -0.1700
Data Index: 6773208 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0841. Min Act: -0.1700
Data Index: 5821023 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0841. Min Act: -0.1700
Data Index: 8196985 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0529. Min Act: -0.1700
Data Index: 2215737 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0529. Min Act: -0.1700
Data Index: 8003930 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0216. Min Act: -0.1700
Data Index: 2785668 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5216. Min Range: -6.5216
Max Act: 5.9904. Min Act: -0.1700
Data Index: 4926404 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0216. Min Act: -0.1700
Data Index: 6868321 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0216. Min Act: -0.1700
Data Index: 3638906 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0216. Min Act: -0.1700
Data Index: 3505859 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5216. Min Range: -6.5216
Max Act: 6.0216. Min Act: -0.1700
Data Index: 1437729 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5216. Min Range: -6.5216
Max Act: 5.9904. Min Act: -0.1700
Data Index: 4282838 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19