Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.5010. Min Act: -0.1700
Data Index: 954530 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.5171. Min Act: -0.1700
Data Index: 497743 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.4847. Min Act: -0.1700
Data Index: 5614200 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.4034. Min Act: -0.1700
Data Index: 4007835 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3707. Min Act: -0.1700
Data Index: 5050720 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3380. Min Act: -0.1700
Data Index: 1583101 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3544. Min Act: -0.1700
Data Index: 2705809 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3380. Min Act: -0.1700
Data Index: 5218809 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3544. Min Act: -0.1700
Data Index: 5385762 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3380. Min Act: -0.1700
Data Index: 6941126 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3707. Min Act: -0.1700
Data Index: 8049238 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3216. Min Act: -0.1700
Data Index: 8189459 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3051. Min Act: -0.1700
Data Index: 7735904 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3216. Min Act: -0.1700
Data Index: 7831380 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3051. Min Act: -0.1700
Data Index: 8363780 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3380. Min Act: -0.1700
Data Index: 4924930 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.2722. Min Act: -0.1700
Data Index: 2227383 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.3216. Min Act: -0.1700
Data Index: 376446 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.2392. Min Act: -0.1700
Data Index: 1777309 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5171. Min Range: -2.5171
Max Act: 2.2722. Min Act: -0.1700
Data Index: 2416889 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19