Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4368 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.8465. Min Act: -0.1700
Data Index: 2402556 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.4715. Min Act: -0.1700
Data Index: 3692826 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3777. Min Act: -0.1695
Data Index: 2457802 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3777. Min Act: -0.1700
Data Index: 8155049 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3152. Min Act: -0.1700
Data Index: 6583729 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.3152. Min Act: -0.1700
Data Index: 8487286 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2840. Min Act: -0.1700
Data Index: 8502419 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2840. Min Act: -0.1700
Data Index: 6202876 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2215. Min Act: -0.1698
Data Index: 499596 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2215. Min Act: -0.1700
Data Index: 4187889 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2215. Min Act: -0.1700
Data Index: 7218282 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.2527. Min Act: -0.1700
Data Index: 8604570 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.1902. Min Act: -0.1699
Data Index: 5010300 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.1590. Min Act: -0.1694
Data Index: 3572918 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.1590. Min Act: -0.1700
Data Index: 4248167 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.1590. Min Act: -0.1700
Data Index: 1261850 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.1590. Min Act: -0.1700
Data Index: 364904 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.1277. Min Act: -0.1700
Data Index: 7735598 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.1590. Min Act: -0.1700
Data Index: 4138106 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8465. Min Range: -7.8465
Max Act: 7.1277. Min Act: -0.1700
Data Index: 6069941 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19