Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 946 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.9547. Min Act: -0.1700
Data Index: 2249424 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.9234. Min Act: -0.1700
Data Index: 2718841 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.8609. Min Act: -0.1700
Data Index: 7393626 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.8297. Min Act: -0.1697
Data Index: 5355089 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.7672. Min Act: -0.1700
Data Index: 4583459 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.7359. Min Act: -0.1700
Data Index: 8705919 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.7359. Min Act: -0.1700
Data Index: 6090537 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6734. Min Act: -0.1699
Data Index: 6869140 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6422. Min Act: -0.1698
Data Index: 4086923 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6422. Min Act: -0.1700
Data Index: 7297512 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.7359. Min Act: -0.1700
Data Index: 2065063 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6734. Min Act: -0.1700
Data Index: 7124857 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.7047. Min Act: -0.1700
Data Index: 3615898 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6422. Min Act: -0.1700
Data Index: 4473943 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.7047. Min Act: -0.1700
Data Index: 1854905 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.7047. Min Act: -0.1695
Data Index: 3769775 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6422. Min Act: -0.1700
Data Index: 8273997 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6734. Min Act: -0.1700
Data Index: 1391857 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6109. Min Act: -0.1700
Data Index: 8406747 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6109. Min Act: -0.1700
Data Index: 3696840 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19