Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5121 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.9210. Min Act: -0.1700
Data Index: 7866073 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.8585. Min Act: -0.1700
Data Index: 3475712 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.7023. Min Act: -0.1700
Data Index: 4658986 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.7023. Min Act: -0.1700
Data Index: 1042781 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.6398. Min Act: -0.1700
Data Index: 4393730 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.6398. Min Act: -0.1700
Data Index: 1268141 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.6710. Min Act: -0.1700
Data Index: 2814052 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.5460. Min Act: -0.1700
Data Index: 8055462 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.5148. Min Act: -0.1700
Data Index: 5129713 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.5148. Min Act: -0.1700
Data Index: 8133477 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.5460. Min Act: -0.1700
Data Index: 5774790 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.5148. Min Act: -0.1700
Data Index: 2291340 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.4835. Min Act: -0.1700
Data Index: 3192060 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.4523. Min Act: -0.1700
Data Index: 3981460 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.4523. Min Act: -0.1700
Data Index: 20298 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.4835. Min Act: -0.1700
Data Index: 593022 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.4210. Min Act: -0.1700
Data Index: 5632199 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.4210. Min Act: -0.1700
Data Index: 3491718 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.4210. Min Act: -0.1700
Data Index: 1581877 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9210. Min Range: -7.9210
Max Act: 7.4210. Min Act: -0.1700
Data Index: 3736974 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19