Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4350. Min Range: -8.4350
Max Act: 8.4350. Min Act: -0.1700
Data Index: 7174713 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.8725. Min Act: -0.1700
Data Index: 911292 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.6225. Min Act: -0.1700
Data Index: 1887861 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.4350. Min Act: -0.1700
Data Index: 3574724 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.3725. Min Act: -0.1700
Data Index: 476016 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.3100. Min Act: -0.1700
Data Index: 4046846 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.2475. Min Act: -0.1700
Data Index: 2002687 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.1850. Min Act: -0.1700
Data Index: 3376707 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.1850. Min Act: -0.1700
Data Index: 1802623 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.0600. Min Act: -0.1700
Data Index: 6915846 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.0288. Min Act: -0.1700
Data Index: 6044098 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4350. Min Range: -8.4350
Max Act: 7.0288. Min Act: -0.1700
Data Index: 6715020 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4350. Min Range: -8.4350
Max Act: 6.9975. Min Act: -0.1700
Data Index: 4063123 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4350. Min Range: -8.4350
Max Act: 6.9350. Min Act: -0.1700
Data Index: 3112212 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4350. Min Range: -8.4350
Max Act: 6.9663. Min Act: -0.1700
Data Index: 5107960 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4350. Min Range: -8.4350
Max Act: 6.9350. Min Act: -0.1700
Data Index: 2735775 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4350. Min Range: -8.4350
Max Act: 6.9038. Min Act: -0.1700
Data Index: 7138407 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4350. Min Range: -8.4350
Max Act: 6.9038. Min Act: -0.1700
Data Index: 1932737 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4350. Min Range: -8.4350
Max Act: 6.8725. Min Act: -0.1700
Data Index: 6145603 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4350. Min Range: -8.4350
Max Act: 6.8725. Min Act: -0.1700
Data Index: 155398 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19