Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.2329. Min Act: -0.1700
Data Index: 5478582 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.1704. Min Act: -0.1700
Data Index: 5931142 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.1079. Min Act: -0.1700
Data Index: 5235816 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.1079. Min Act: -0.1700
Data Index: 7902046 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.0454. Min Act: -0.1700
Data Index: 6824589 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.0454. Min Act: -0.1700
Data Index: 1868379 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.0454. Min Act: -0.1700
Data Index: 8565836 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.0454. Min Act: -0.1700
Data Index: 3009140 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2329. Min Range: -8.2329
Max Act: 8.0454. Min Act: -0.1700
Data Index: 877571 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.9829. Min Act: -0.1700
Data Index: 7372876 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.9829. Min Act: -0.1700
Data Index: 2401597 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.9829. Min Act: -0.1700
Data Index: 7685340 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.9829. Min Act: -0.1700
Data Index: 7611917 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.9204. Min Act: -0.1700
Data Index: 7931541 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.9204. Min Act: -0.1700
Data Index: 7828781 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.9204. Min Act: -0.1700
Data Index: 2994007 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.9204. Min Act: -0.1700
Data Index: 8645748 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.8579. Min Act: -0.1700
Data Index: 5907648 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.8579. Min Act: -0.1700
Data Index: 18251 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2329. Min Range: -8.2329
Max Act: 7.7954. Min Act: -0.1700
Data Index: 6648787 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19