Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.7060. Min Act: -0.1700
Data Index: 7622068 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.7060. Min Act: -0.1700
Data Index: 7879223 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.6435. Min Act: -0.1700
Data Index: 2410445 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.6435. Min Act: -0.1700
Data Index: 370969 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.6435. Min Act: -0.1700
Data Index: 8365533 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.6123. Min Act: -0.1700
Data Index: 1911308 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.6123. Min Act: -0.1700
Data Index: 965523 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.5498. Min Act: -0.1700
Data Index: 1223412 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.5498. Min Act: -0.1700
Data Index: 6067725 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.5498. Min Act: -0.1700
Data Index: 6975014 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.5498. Min Act: -0.1700
Data Index: 2692465 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.5498. Min Act: -0.1700
Data Index: 1835792 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.5498. Min Act: -0.1700
Data Index: 8365531 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.4560. Min Act: -0.1700
Data Index: 4200276 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.4560. Min Act: -0.1700
Data Index: 115992 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.4873. Min Act: -0.1700
Data Index: 2992371 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.3623. Min Act: -0.1700
Data Index: 3757085 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.3623. Min Act: -0.1700
Data Index: 6067730 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.4560. Min Act: -0.1700
Data Index: 1951717 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7060. Min Range: -5.7060
Max Act: 5.3935. Min Act: -0.1700
Data Index: 7958462 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19