Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5382 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0850. Min Range: -8.0850
Max Act: 8.0850. Min Act: -0.1700
Data Index: 2139651 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.9600. Min Act: -0.1700
Data Index: 7370836 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.8975. Min Act: -0.1700
Data Index: 3687766 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.8350. Min Act: -0.1700
Data Index: 4252017 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.8975. Min Act: -0.1700
Data Index: 563140 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.8350. Min Act: -0.1700
Data Index: 5940922 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.7725. Min Act: -0.1700
Data Index: 2668211 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.7725. Min Act: -0.1700
Data Index: 2918851 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.7100. Min Act: -0.1700
Data Index: 6511294 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.7100. Min Act: -0.1700
Data Index: 4352641 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.6475. Min Act: -0.1700
Data Index: 8540628 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.6475. Min Act: -0.1700
Data Index: 3513467 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.5538. Min Act: -0.1700
Data Index: 3898331 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.5538. Min Act: -0.1700
Data Index: 6851050 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.5225. Min Act: -0.1700
Data Index: 5622843 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.5225. Min Act: -0.1700
Data Index: 4468158 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.4913. Min Act: -0.1700
Data Index: 4709172 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.4913. Min Act: -0.1700
Data Index: 4909594 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.4913. Min Act: -0.1700
Data Index: 7461097 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0850. Min Range: -8.0850
Max Act: 7.4600. Min Act: -0.1700
Data Index: 3091807 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19