Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.2510. Min Act: -0.0067
Data Index: 3959438 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.1103. Min Act: -0.0663
Data Index: 3136035 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.1103. Min Act: -0.0220
Data Index: 3959405 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.1190. Min Act: 0.0110
Data Index: 3959437 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0927. Min Act: 0.1331
Data Index: 7721667 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0927. Min Act: -0.0502
Data Index: 7306634 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0840. Min Act: -0.0611
Data Index: 1164063 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0840. Min Act: -0.0676
Data Index: 6041975 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0665. Min Act: -0.0742
Data Index: 840911 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0752. Min Act: 0.0471
Data Index: 1247696 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0927. Min Act: -0.0737
Data Index: 6783399 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0665. Min Act: -0.0274
Data Index: 7589901 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0578. Min Act: -0.0602
Data Index: 2062712 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0665. Min Act: -0.0875
Data Index: 6065334 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0752. Min Act: 0.1097
Data Index: 3626987 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0665. Min Act: -0.0786
Data Index: 3597802 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0665. Min Act: -0.0959
Data Index: 7141037 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0578. Min Act: -0.0482
Data Index: 3678836 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0665. Min Act: -0.1158
Data Index: 4584708 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2510. Min Range: -1.2510
Max Act: 1.0578. Min Act: 0.1344
Data Index: 3626985 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19