Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 8715565 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 1312828 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 5612779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 1913695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 1489867 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 1489863 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 1489862 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 1489868 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9089. Min Act: -0.1700
Data Index: 4835733 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9402. Min Act: -0.1700
Data Index: 1489869 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9089. Min Act: -0.1700
Data Index: 1489865 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9089. Min Act: -0.1700
Data Index: 3466350 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9089. Min Act: -0.1700
Data Index: 3448239 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9089. Min Act: -0.1700
Data Index: 6045810 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9089. Min Act: -0.1700
Data Index: 6045806 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.9089. Min Act: -0.1700
Data Index: 5661645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.8776. Min Act: -0.1700
Data Index: 3130969 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.8464. Min Act: -0.1700
Data Index: 593048 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.8776. Min Act: -0.1700
Data Index: 6045814 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9402. Min Range: -3.9402
Max Act: 3.8776. Min Act: -0.1700
Data Index: 6045816 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19