Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2714 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.8434. Min Act: -0.1700
Data Index: 1604642 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.8121. Min Act: -0.1700
Data Index: 7953512 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.7496. Min Act: -0.1700
Data Index: 23702 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6871. Min Act: -0.1700
Data Index: 6891093 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.7184. Min Act: -0.1700
Data Index: 6218578 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6871. Min Act: -0.1700
Data Index: 7169491 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6871. Min Act: -0.1700
Data Index: 6231673 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6871. Min Act: -0.1700
Data Index: 7695972 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6871. Min Act: -0.1700
Data Index: 5714857 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6871. Min Act: -0.1700
Data Index: 8574805 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6871. Min Act: -0.1700
Data Index: 4613021 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6559. Min Act: -0.1700
Data Index: 3400808 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6246. Min Act: -0.1700
Data Index: 2096186 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6559. Min Act: -0.1700
Data Index: 3752868 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6559. Min Act: -0.1700
Data Index: 5919492 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6246. Min Act: -0.1700
Data Index: 5075792 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6559. Min Act: -0.1700
Data Index: 4606380 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6246. Min Act: -0.1700
Data Index: 1861831 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6246. Min Act: -0.1700
Data Index: 5866371 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8434. Min Range: -4.8434
Max Act: 4.6246. Min Act: -0.1700
Data Index: 6240211 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19