Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1759 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.3715. Min Act: -0.1700
Data Index: 6735461 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.2777. Min Act: -0.1700
Data Index: 2830165 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.1840. Min Act: -0.1700
Data Index: 1988336 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.1215. Min Act: -0.1700
Data Index: 3742601 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.1527. Min Act: -0.1700
Data Index: 7546618 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0590. Min Act: -0.1700
Data Index: 3058138 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0902. Min Act: -0.1700
Data Index: 6665054 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0590. Min Act: -0.1700
Data Index: 6444079 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0590. Min Act: -0.1700
Data Index: 1827397 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0590. Min Act: -0.1700
Data Index: 4655682 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0277. Min Act: -0.1700
Data Index: 1542487 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0277. Min Act: -0.1700
Data Index: 427208 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0277. Min Act: -0.1700
Data Index: 5164877 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3715. Min Range: -7.3715
Max Act: 7.0277. Min Act: -0.1700
Data Index: 8557335 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3715. Min Range: -7.3715
Max Act: 6.9965. Min Act: -0.1700
Data Index: 4856934 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3715. Min Range: -7.3715
Max Act: 6.9965. Min Act: -0.1700
Data Index: 5352527 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3715. Min Range: -7.3715
Max Act: 6.9965. Min Act: -0.1700
Data Index: 8369919 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3715. Min Range: -7.3715
Max Act: 6.9652. Min Act: -0.1700
Data Index: 2338743 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3715. Min Range: -7.3715
Max Act: 6.9340. Min Act: -0.1700
Data Index: 4619196 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3715. Min Range: -7.3715
Max Act: 6.9340. Min Act: -0.1700
Data Index: 6444100 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19