Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3211 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.7618. Min Act: -0.1700
Data Index: 948723 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.6681. Min Act: -0.1700
Data Index: 6576390 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.6056. Min Act: -0.1700
Data Index: 2780657 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.4181. Min Act: -0.1700
Data Index: 2173864 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.3556. Min Act: -0.1700
Data Index: 5629633 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.3556. Min Act: -0.1700
Data Index: 3496547 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.3243. Min Act: -0.1700
Data Index: 6360622 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.2931. Min Act: -0.1700
Data Index: 5090517 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.2618. Min Act: -0.1700
Data Index: 7321856 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.2931. Min Act: -0.1700
Data Index: 4707884 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.2618. Min Act: -0.1700
Data Index: 2757399 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.2618. Min Act: -0.1700
Data Index: 5919305 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.2306. Min Act: -0.1700
Data Index: 667805 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.1993. Min Act: -0.1700
Data Index: 4184138 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.2306. Min Act: -0.1700
Data Index: 5164611 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.1993. Min Act: -0.1700
Data Index: 5058503 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.1993. Min Act: -0.1700
Data Index: 8718052 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.1681. Min Act: -0.1700
Data Index: 95004 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.1368. Min Act: -0.1700
Data Index: 1341654 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7618. Min Range: -7.7618
Max Act: 7.1681. Min Act: -0.1700
Data Index: 3161965 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19