Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5812 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1784. Min Range: -6.1784
Max Act: 6.1784. Min Act: -0.1700
Data Index: 2226967 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1784. Min Range: -6.1784
Max Act: 6.1159. Min Act: -0.1700
Data Index: 8087562 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1784. Min Range: -6.1784
Max Act: 6.0534. Min Act: -0.1700
Data Index: 3702084 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1784. Min Range: -6.1784
Max Act: 6.0534. Min Act: -0.1700
Data Index: 8152703 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1784. Min Range: -6.1784
Max Act: 6.0222. Min Act: -0.1700
Data Index: 6471068 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.9909. Min Act: -0.1700
Data Index: 4519266 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.9909. Min Act: -0.1700
Data Index: 2487229 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.9597. Min Act: -0.1700
Data Index: 6735682 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8972. Min Act: -0.1700
Data Index: 2219381 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8972. Min Act: -0.1700
Data Index: 8156952 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8659. Min Act: -0.1700
Data Index: 8179334 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8659. Min Act: -0.1700
Data Index: 5510105 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8659. Min Act: -0.1700
Data Index: 5814734 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8347. Min Act: -0.1700
Data Index: 3852054 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8347. Min Act: -0.1700
Data Index: 7207906 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8347. Min Act: -0.1700
Data Index: 8593893 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8034. Min Act: -0.1700
Data Index: 6557352 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8034. Min Act: -0.1700
Data Index: 7099727 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.7722. Min Act: -0.1700
Data Index: 1674127 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1784. Min Range: -6.1784
Max Act: 5.8034. Min Act: -0.1700
Data Index: 6031239 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19