Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8997. Min Act: -0.1700
Data Index: 1890365 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8484. Min Act: -0.1700
Data Index: 5875645 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8484. Min Act: -0.1700
Data Index: 1492929 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8313. Min Act: -0.1700
Data Index: 4701613 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8484. Min Act: -0.1700
Data Index: 4544029 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8227. Min Act: -0.1698
Data Index: 3218383 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8313. Min Act: -0.1700
Data Index: 6242358 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8227. Min Act: -0.1700
Data Index: 7733102 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8055. Min Act: -0.1700
Data Index: 1275681 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.8055. Min Act: -0.1700
Data Index: 8391662 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7969. Min Act: -0.1700
Data Index: 8398489 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7883. Min Act: -0.1700
Data Index: 2556192 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7969. Min Act: -0.1700
Data Index: 7585196 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7969. Min Act: -0.1700
Data Index: 2091235 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7883. Min Act: -0.1700
Data Index: 8109136 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7969. Min Act: -0.1700
Data Index: 272693 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7969. Min Act: -0.1700
Data Index: 8059555 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7883. Min Act: -0.1700
Data Index: 4825717 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7883. Min Act: -0.1700
Data Index: 7365080 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8997. Min Range: -1.8997
Max Act: 1.7969. Min Act: -0.1700
Data Index: 7365079 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19