Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.4041. Min Act: -0.1700
Data Index: 5151166 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.3728. Min Act: -0.1700
Data Index: 7631501 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.3416. Min Act: -0.1700
Data Index: 4777360 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.2791. Min Act: -0.1700
Data Index: 8272699 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.2478. Min Act: -0.1700
Data Index: 4873895 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.2478. Min Act: -0.1700
Data Index: 6959968 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.2478. Min Act: -0.1700
Data Index: 4726954 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.2166. Min Act: -0.1700
Data Index: 5802408 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.2166. Min Act: -0.1700
Data Index: 5883656 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1853. Min Act: -0.1700
Data Index: 8457555 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1853. Min Act: -0.1700
Data Index: 7699488 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1853. Min Act: -0.1700
Data Index: 7804558 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1541. Min Act: -0.1700
Data Index: 4420767 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1541. Min Act: -0.1700
Data Index: 4590857 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1853. Min Act: -0.1700
Data Index: 2805789 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.0916. Min Act: -0.1700
Data Index: 4585655 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1228. Min Act: -0.1700
Data Index: 4594868 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1228. Min Act: -0.1700
Data Index: 5069871 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1228. Min Act: -0.1700
Data Index: 3473969 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4041. Min Range: -4.4041
Max Act: 4.1541. Min Act: -0.1700
Data Index: 6971567 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19