Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3871. Min Range: -5.3871
Max Act: 5.3871. Min Act: -0.1700
Data Index: 4506098 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.8559. Min Act: -0.1700
Data Index: 5648080 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.8246. Min Act: -0.1700
Data Index: 4490226 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.6059. Min Act: -0.1700
Data Index: 967037 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.6059. Min Act: -0.1700
Data Index: 6313 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.6059. Min Act: -0.1700
Data Index: 3455513 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.5746. Min Act: -0.1700
Data Index: 5635188 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.5434. Min Act: -0.1700
Data Index: 7712859 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.5746. Min Act: -0.1700
Data Index: 6047446 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.5434. Min Act: -0.1700
Data Index: 5635191 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4809. Min Act: -0.1700
Data Index: 5635183 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.5121. Min Act: -0.1700
Data Index: 6317 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4496. Min Act: -0.1700
Data Index: 609690 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4496. Min Act: -0.1700
Data Index: 4893749 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4496. Min Act: -0.1700
Data Index: 6320 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4496. Min Act: -0.1700
Data Index: 6321 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4496. Min Act: -0.1700
Data Index: 2509067 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4496. Min Act: -0.1700
Data Index: 6330 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4496. Min Act: -0.1700
Data Index: 7571890 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3871. Min Range: -5.3871
Max Act: 4.4496. Min Act: -0.1700
Data Index: 7295200 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19