Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6102 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5586. Min Range: -10.5586
Max Act: 10.5586. Min Act: -0.1700
Data Index: 7822848 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.7461. Min Act: -0.1700
Data Index: 3321005 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.6211. Min Act: -0.1700
Data Index: 4309425 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.7461. Min Act: -0.1700
Data Index: 227530 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.5586. Min Act: -0.1700
Data Index: 6087761 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.4961. Min Act: -0.1699
Data Index: 2037123 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.5586. Min Act: -0.1700
Data Index: 5052555 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.4961. Min Act: -0.1700
Data Index: 8225679 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.4336. Min Act: -0.1700
Data Index: 6122208 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.4336. Min Act: -0.1700
Data Index: 416744 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.4336. Min Act: -0.1700
Data Index: 1630036 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.3711. Min Act: -0.1700
Data Index: 3163884 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.3711. Min Act: -0.1700
Data Index: 4696722 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.3086. Min Act: -0.1700
Data Index: 3838429 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.3086. Min Act: -0.1700
Data Index: 4908890 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.3086. Min Act: -0.1700
Data Index: 1971823 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.2461. Min Act: -0.1700
Data Index: 6459938 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.2461. Min Act: -0.1700
Data Index: 1070113 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.2461. Min Act: -0.1700
Data Index: 550353 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5586. Min Range: -10.5586
Max Act: 9.3086. Min Act: -0.1700
Data Index: 4127783 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19