Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1905 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2557. Min Range: -10.2557
Max Act: 10.2557. Min Act: -0.1700
Data Index: 1810759 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.6932. Min Act: -0.1700
Data Index: 6059395 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.6307. Min Act: -0.1700
Data Index: 8149587 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.5682. Min Act: -0.1700
Data Index: 7533418 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.5682. Min Act: -0.1700
Data Index: 6761211 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.5057. Min Act: -0.1700
Data Index: 496736 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.5057. Min Act: -0.1700
Data Index: 6791999 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.5057. Min Act: -0.1700
Data Index: 2357551 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.4432. Min Act: -0.1700
Data Index: 8339479 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.4432. Min Act: -0.1700
Data Index: 3125153 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.3807. Min Act: -0.1700
Data Index: 2072290 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.3807. Min Act: -0.1700
Data Index: 3972219 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.3807. Min Act: -0.1700
Data Index: 6042530 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.3807. Min Act: -0.1700
Data Index: 693612 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.3807. Min Act: -0.1700
Data Index: 571799 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.3182. Min Act: -0.1700
Data Index: 1206130 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.2557. Min Act: -0.1700
Data Index: 3183023 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.3182. Min Act: -0.1700
Data Index: 2371842 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.2557. Min Act: -0.1700
Data Index: 4780702 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2557. Min Range: -10.2557
Max Act: 9.2557. Min Act: -0.1700
Data Index: 7060178 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19