Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.3268. Min Act: -0.1700
Data Index: 7778589 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.3268. Min Act: -0.1700
Data Index: 4022910 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.2640. Min Act: -0.1700
Data Index: 8543974 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.2640. Min Act: -0.1700
Data Index: 2230718 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.2483. Min Act: -0.1700
Data Index: 1932732 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.2326. Min Act: -0.1700
Data Index: 6649503 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.2169. Min Act: -0.1700
Data Index: 2144773 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.2169. Min Act: -0.1700
Data Index: 6015572 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.1382. Min Act: -0.1700
Data Index: 1154443 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.1382. Min Act: -0.1700
Data Index: 4255044 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.1225. Min Act: -0.1700
Data Index: 2743641 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.1067. Min Act: -0.1700
Data Index: 4941941 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.1067. Min Act: -0.1700
Data Index: 4706974 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.0909. Min Act: -0.1700
Data Index: 1786771 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.0909. Min Act: -0.1700
Data Index: 3251731 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.1067. Min Act: -0.1700
Data Index: 528159 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.1067. Min Act: -0.1700
Data Index: 7414279 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.1067. Min Act: -0.1700
Data Index: 7630667 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.0752. Min Act: -0.1700
Data Index: 4692499 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3268. Min Range: -3.3268
Max Act: 3.0752. Min Act: -0.1700
Data Index: 3564155 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19