Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.5177. Min Act: -0.1700
Data Index: 7002847 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.3302. Min Act: -0.1700
Data Index: 2501985 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.3302. Min Act: -0.1700
Data Index: 8629137 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.2989. Min Act: -0.1700
Data Index: 6325773 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.2989. Min Act: -0.1700
Data Index: 2175894 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.2364. Min Act: -0.1700
Data Index: 8376790 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.2364. Min Act: -0.1700
Data Index: 4239449 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.2052. Min Act: -0.1700
Data Index: 4555675 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1739. Min Act: -0.1700
Data Index: 5688944 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1739. Min Act: -0.1700
Data Index: 2071109 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1739. Min Act: -0.1700
Data Index: 2333659 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1739. Min Act: -0.1700
Data Index: 8674321 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1114. Min Act: -0.1700
Data Index: 5571091 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1427. Min Act: -0.1700
Data Index: 871600 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1427. Min Act: -0.1700
Data Index: 4394291 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1114. Min Act: -0.1700
Data Index: 1141870 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1427. Min Act: -0.1700
Data Index: 7333003 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.1114. Min Act: -0.1700
Data Index: 7333738 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.0802. Min Act: -0.1700
Data Index: 5156009 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5177. Min Range: -5.5177
Max Act: 5.0802. Min Act: -0.1700
Data Index: 7237670 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19