Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3934 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.5114. Min Act: -0.1700
Data Index: 2667979 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.4489. Min Act: -0.1700
Data Index: 647528 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.3239. Min Act: -0.1700
Data Index: 4180183 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.3239. Min Act: -0.1700
Data Index: 8158149 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.2614. Min Act: -0.1700
Data Index: 4279377 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.2614. Min Act: -0.1700
Data Index: 7419204 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.1989. Min Act: -0.1700
Data Index: 2876562 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.1989. Min Act: -0.1700
Data Index: 3407048 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.1364. Min Act: -0.1700
Data Index: 7410992 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.1364. Min Act: -0.1700
Data Index: 7671949 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.1364. Min Act: -0.1700
Data Index: 4410034 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.1364. Min Act: -0.1700
Data Index: 8818568 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.1364. Min Act: -0.1700
Data Index: 4746863 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.0739. Min Act: -0.1700
Data Index: 3526107 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.0739. Min Act: -0.1700
Data Index: 5482457 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.0114. Min Act: -0.1700
Data Index: 7620191 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5114. Min Range: -8.5114
Max Act: 8.0739. Min Act: -0.1700
Data Index: 2773833 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5114. Min Range: -8.5114
Max Act: 7.9489. Min Act: -0.1700
Data Index: 8094494 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5114. Min Range: -8.5114
Max Act: 7.9489. Min Act: -0.1700
Data Index: 5938339 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5114. Min Range: -8.5114
Max Act: 7.9489. Min Act: -0.1700
Data Index: 7108986 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19