Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6274 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5216. Min Range: -7.5216
Max Act: 7.5216. Min Act: -0.1700
Data Index: 3889970 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5216. Min Range: -7.5216
Max Act: 7.3966. Min Act: -0.1700
Data Index: 370929 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5216. Min Range: -7.5216
Max Act: 7.3341. Min Act: -0.1700
Data Index: 2552288 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5216. Min Range: -7.5216
Max Act: 7.1154. Min Act: -0.1700
Data Index: 1860076 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5216. Min Range: -7.5216
Max Act: 7.1154. Min Act: -0.1700
Data Index: 7593129 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5216. Min Range: -7.5216
Max Act: 7.1154. Min Act: -0.1700
Data Index: 5784296 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.9904. Min Act: -0.1700
Data Index: 2383667 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.9904. Min Act: -0.1700
Data Index: 4409471 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.9904. Min Act: -0.1700
Data Index: 2411053 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.9904. Min Act: -0.1700
Data Index: 3068665 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.9591. Min Act: -0.1700
Data Index: 2494319 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.8966. Min Act: -0.1700
Data Index: 2432557 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.9279. Min Act: -0.1700
Data Index: 507865 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.9279. Min Act: -0.1700
Data Index: 3102096 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.9279. Min Act: -0.1700
Data Index: 38905 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.8966. Min Act: -0.1700
Data Index: 8534663 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.8654. Min Act: -0.1700
Data Index: 2432555 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.8341. Min Act: -0.1700
Data Index: 2406613 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.8029. Min Act: -0.1700
Data Index: 6801423 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5216. Min Range: -7.5216
Max Act: 6.8029. Min Act: -0.1700
Data Index: 256065 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19