Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1433. Min Range: -6.1433
Max Act: 6.1433. Min Act: -0.1700
Data Index: 11404 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1433. Min Range: -6.1433
Max Act: 6.0496. Min Act: -0.1700
Data Index: 2971385 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.9246. Min Act: -0.1700
Data Index: 4600013 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.9246. Min Act: -0.1700
Data Index: 4279965 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.8933. Min Act: -0.1700
Data Index: 6302622 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.8308. Min Act: -0.1700
Data Index: 4725479 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.7683. Min Act: -0.1700
Data Index: 2642846 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.7058. Min Act: -0.1700
Data Index: 3282431 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.6746. Min Act: -0.1700
Data Index: 8696218 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.6746. Min Act: -0.1700
Data Index: 2788455 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.6433. Min Act: -0.1700
Data Index: 1276492 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.6433. Min Act: -0.1700
Data Index: 4158269 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.6121. Min Act: -0.1700
Data Index: 7828740 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.5496. Min Act: -0.1700
Data Index: 7776628 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.5808. Min Act: -0.1700
Data Index: 3474843 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.4871. Min Act: -0.1700
Data Index: 1550873 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.5183. Min Act: -0.1700
Data Index: 4812172 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.4871. Min Act: -0.1700
Data Index: 5800978 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.5183. Min Act: -0.1700
Data Index: 3432026 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1433. Min Range: -6.1433
Max Act: 5.4871. Min Act: -0.1700
Data Index: 1975563 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19