Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.9880. Min Act: -0.1700
Data Index: 8607020 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.9568. Min Act: -0.1700
Data Index: 7239643 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.8943. Min Act: -0.1700
Data Index: 2681700 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.7068. Min Act: -0.1700
Data Index: 917927 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.7068. Min Act: -0.1700
Data Index: 1100144 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.6755. Min Act: -0.1700
Data Index: 423721 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.6443. Min Act: -0.1700
Data Index: 5429638 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.6755. Min Act: -0.1700
Data Index: 8465955 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.6755. Min Act: -0.1700
Data Index: 4352925 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.6443. Min Act: -0.1700
Data Index: 5958717 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.6130. Min Act: -0.1700
Data Index: 4474108 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.5818. Min Act: -0.1700
Data Index: 4982175 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.6130. Min Act: -0.1700
Data Index: 3317507 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.5818. Min Act: -0.1700
Data Index: 3344365 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.5505. Min Act: -0.1700
Data Index: 644149 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.5505. Min Act: -0.1700
Data Index: 5537320 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.5505. Min Act: -0.1700
Data Index: 1720705 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.5505. Min Act: -0.1700
Data Index: 1469896 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.5193. Min Act: -0.1700
Data Index: 3979591 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9880. Min Range: -6.9880
Max Act: 6.4880. Min Act: -0.1700
Data Index: 8500232 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19