Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.9013. Min Act: -0.1700
Data Index: 1244939 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8842. Min Act: -0.1700
Data Index: 3006228 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8671. Min Act: -0.1700
Data Index: 3714307 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8671. Min Act: -0.1700
Data Index: 3760001 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8671. Min Act: -0.1700
Data Index: 1727403 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8500. Min Act: -0.1700
Data Index: 3658165 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8328. Min Act: -0.1700
Data Index: 5446522 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 6902211 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 6331521 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 5939360 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 8577901 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 8062719 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 7571122 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.7985. Min Act: -0.1700
Data Index: 1541680 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 6173409 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 5313996 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.7985. Min Act: -0.1700
Data Index: 2744504 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.7985. Min Act: -0.1700
Data Index: 5069829 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.8157. Min Act: -0.1700
Data Index: 4395437 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9013. Min Range: -1.9013
Max Act: 1.7985. Min Act: -0.1700
Data Index: 4229282 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19