Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5156. Min Range: -6.5156
Max Act: 6.5156. Min Act: -0.1700
Data Index: 3283868 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5156. Min Range: -6.5156
Max Act: 6.3593. Min Act: -0.1700
Data Index: 8503708 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5156. Min Range: -6.5156
Max Act: 6.2343. Min Act: -0.1700
Data Index: 8315039 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5156. Min Range: -6.5156
Max Act: 6.2031. Min Act: -0.1700
Data Index: 7059248 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5156. Min Range: -6.5156
Max Act: 6.1093. Min Act: -0.1699
Data Index: 1756709 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5156. Min Range: -6.5156
Max Act: 6.1093. Min Act: -0.1698
Data Index: 1044388 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5156. Min Range: -6.5156
Max Act: 6.1093. Min Act: -0.1700
Data Index: 1714476 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5156. Min Range: -6.5156
Max Act: 6.1093. Min Act: -0.1699
Data Index: 1756711 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.9531. Min Act: -0.1700
Data Index: 8337984 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.9843. Min Act: -0.1700
Data Index: 6250116 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1756705 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.9531. Min Act: -0.1700
Data Index: 5422422 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1122545 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1756712 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.8593. Min Act: -0.1700
Data Index: 1830434 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.8906. Min Act: -0.1700
Data Index: 1725868 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.8281. Min Act: -0.1700
Data Index: 3580169 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.8281. Min Act: -0.1700
Data Index: 2475252 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.7968. Min Act: -0.1700
Data Index: 1062798 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5156. Min Range: -6.5156
Max Act: 5.7656. Min Act: -0.1700
Data Index: 1714477 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19