Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.3371. Min Act: -0.1700
Data Index: 8191750 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.3371. Min Act: -0.1700
Data Index: 4220808 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.2434. Min Act: -0.1700
Data Index: 4348176 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.2434. Min Act: -0.1700
Data Index: 5479779 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0871. Min Act: -0.1700
Data Index: 7639201 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.1808. Min Act: -0.1700
Data Index: 7829536 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0871. Min Act: -0.1700
Data Index: 5383247 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0558. Min Act: -0.1700
Data Index: 6351373 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0558. Min Act: -0.1700
Data Index: 2045126 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3371. Min Range: -4.3371
Max Act: 3.9777. Min Act: -0.1700
Data Index: 4757692 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0246. Min Act: -0.1700
Data Index: 1279817 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0558. Min Act: -0.1700
Data Index: 2074672 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0558. Min Act: -0.1700
Data Index: 965440 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0089. Min Act: -0.1700
Data Index: 457741 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3371. Min Range: -4.3371
Max Act: 3.9933. Min Act: -0.1700
Data Index: 3363524 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0558. Min Act: -0.1700
Data Index: 4909632 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3371. Min Range: -4.3371
Max Act: 3.9308. Min Act: -0.1700
Data Index: 6396098 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3371. Min Range: -4.3371
Max Act: 3.9620. Min Act: -0.1700
Data Index: 499402 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0089. Min Act: -0.1700
Data Index: 5152199 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3371. Min Range: -4.3371
Max Act: 4.0089. Min Act: -0.1700
Data Index: 1180069 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19