Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.3729. Min Act: -0.1700
Data Index: 5042946 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.3258. Min Act: -0.1700
Data Index: 3434261 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2630. Min Act: -0.1700
Data Index: 7582475 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2473. Min Act: -0.1700
Data Index: 879140 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2316. Min Act: -0.1700
Data Index: 396543 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2473. Min Act: -0.1700
Data Index: 6619537 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2158. Min Act: -0.1700
Data Index: 5994411 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2158. Min Act: -0.1700
Data Index: 7858160 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2316. Min Act: -0.1700
Data Index: 3230363 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2158. Min Act: -0.1700
Data Index: 6049390 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2158. Min Act: -0.1700
Data Index: 5534593 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2158. Min Act: -0.1700
Data Index: 6137433 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.2001. Min Act: -0.1700
Data Index: 2973069 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.1844. Min Act: -0.1700
Data Index: 5072769 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.1844. Min Act: -0.1700
Data Index: 7433428 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.1844. Min Act: -0.1700
Data Index: 8602250 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.1844. Min Act: -0.1700
Data Index: 7950314 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.1687. Min Act: -0.1700
Data Index: 7854698 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.1687. Min Act: -0.1700
Data Index: 5184480 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3729. Min Range: -3.3729
Max Act: 3.1687. Min Act: -0.1700
Data Index: 8598243 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19