Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3737 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.8375. Min Act: -0.1700
Data Index: 7147324 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.8219. Min Act: -0.1700
Data Index: 3413172 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.8063. Min Act: -0.1700
Data Index: 3833348 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.7593. Min Act: -0.1700
Data Index: 1146477 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.7593. Min Act: -0.1700
Data Index: 2445391 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.7437. Min Act: -0.1700
Data Index: 3101978 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.7281. Min Act: -0.1700
Data Index: 8479587 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.7124. Min Act: -0.1700
Data Index: 7704231 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.7124. Min Act: -0.1700
Data Index: 540517 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6968. Min Act: -0.1700
Data Index: 2895302 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6968. Min Act: -0.1700
Data Index: 1154774 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6811. Min Act: -0.1700
Data Index: 4555008 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6498. Min Act: -0.1700
Data Index: 7494420 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6498. Min Act: -0.1700
Data Index: 5496454 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6498. Min Act: -0.1700
Data Index: 8753970 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6342. Min Act: -0.1700
Data Index: 4563969 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6655. Min Act: -0.1700
Data Index: 993459 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6342. Min Act: -0.1700
Data Index: 1724511 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6498. Min Act: -0.1700
Data Index: 5276076 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8375. Min Range: -3.8375
Max Act: 3.6342. Min Act: -0.1700
Data Index: 4544000 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19