Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2638. Min Act: -0.1700
Data Index: 3040205 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2638. Min Act: -0.1700
Data Index: 7849010 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2638. Min Act: -0.1700
Data Index: 1653434 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2638. Min Act: -0.1700
Data Index: 320261 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2325. Min Act: -0.1700
Data Index: 7492322 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2325. Min Act: -0.1700
Data Index: 753338 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2325. Min Act: -0.1700
Data Index: 6493324 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2325. Min Act: -0.1700
Data Index: 6278768 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2325. Min Act: -0.1700
Data Index: 2203435 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2325. Min Act: -0.1700
Data Index: 639560 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2325. Min Act: -0.1700
Data Index: 3596656 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2325. Min Act: -0.1700
Data Index: 4416703 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2013. Min Act: -0.1700
Data Index: 1160541 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2013. Min Act: -0.1700
Data Index: 5308755 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2013. Min Act: -0.1700
Data Index: 4649346 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2013. Min Act: -0.1700
Data Index: 608541 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2013. Min Act: -0.1700
Data Index: 778635 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2013. Min Act: -0.1700
Data Index: 324069 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2013. Min Act: -0.1700
Data Index: 2071396 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2638. Min Range: -4.2638
Max Act: 4.2013. Min Act: -0.1700
Data Index: 1571216 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19