Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4742 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.7639. Min Act: -0.1700
Data Index: 5259555 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.5452. Min Act: -0.1700
Data Index: 8195103 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2952. Min Act: -0.1700
Data Index: 193550 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2014. Min Act: -0.1700
Data Index: 1051330 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4482116 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.8889. Min Act: -0.1700
Data Index: 4794740 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.7639. Min Act: -0.1700
Data Index: 5117814 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.7327. Min Act: -0.1700
Data Index: 8761830 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.7639. Min Act: -0.1700
Data Index: 5432741 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.7014. Min Act: -0.1700
Data Index: 3045280 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.7014. Min Act: -0.1700
Data Index: 4278201 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.7014. Min Act: -0.1700
Data Index: 883443 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.6702. Min Act: -0.1700
Data Index: 3788286 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.6702. Min Act: -0.1700
Data Index: 861884 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.6389. Min Act: -0.1700
Data Index: 6255022 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.6389. Min Act: -0.1700
Data Index: 1698552 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.6389. Min Act: -0.1700
Data Index: 7597955 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.6077. Min Act: -0.1700
Data Index: 7034835 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.6077. Min Act: -0.1700
Data Index: 7896332 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7639. Min Range: -6.7639
Max Act: 5.5452. Min Act: -0.1700
Data Index: 5435993 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19