Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2307 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2199. Min Range: -4.2199
Max Act: 4.2199. Min Act: -0.1700
Data Index: 4867713 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2199. Min Range: -4.2199
Max Act: 4.0011. Min Act: -0.1700
Data Index: 2858527 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.9074. Min Act: -0.1700
Data Index: 5763079 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.9074. Min Act: -0.1700
Data Index: 368517 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.9074. Min Act: -0.1700
Data Index: 6000983 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.8448. Min Act: -0.1700
Data Index: 689908 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.8448. Min Act: -0.1700
Data Index: 4021524 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.8448. Min Act: -0.1700
Data Index: 8650261 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.8136. Min Act: -0.1700
Data Index: 7445895 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.7197. Min Act: -0.1700
Data Index: 2840562 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.7510. Min Act: -0.1700
Data Index: 2915438 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.6884. Min Act: -0.1700
Data Index: 6242665 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.7197. Min Act: -0.1700
Data Index: 6242664 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.6884. Min Act: -0.1700
Data Index: 3821441 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.6571. Min Act: -0.1700
Data Index: 3102596 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.6884. Min Act: -0.1700
Data Index: 944926 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.6571. Min Act: -0.1700
Data Index: 5970847 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.6884. Min Act: -0.1700
Data Index: 17011 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.5945. Min Act: -0.1700
Data Index: 1708263 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2199. Min Range: -4.2199
Max Act: 3.6571. Min Act: -0.1700
Data Index: 3824202 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19