Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.2139. Min Act: -0.1700
Data Index: 7597277 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1514. Min Act: -0.1700
Data Index: 3553309 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1514. Min Act: -0.1700
Data Index: 1106949 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1357. Min Act: -0.1700
Data Index: 409587 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1357. Min Act: -0.1700
Data Index: 8343562 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1357. Min Act: -0.1700
Data Index: 8132957 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1201. Min Act: -0.1700
Data Index: 8688543 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1201. Min Act: -0.1700
Data Index: 4493748 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0889. Min Act: -0.1700
Data Index: 3981071 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1045. Min Act: -0.1700
Data Index: 8719738 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1201. Min Act: -0.1700
Data Index: 7620091 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.1045. Min Act: -0.1700
Data Index: 685033 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0889. Min Act: -0.1700
Data Index: 4027515 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0889. Min Act: -0.1700
Data Index: 1720019 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0732. Min Act: -0.1700
Data Index: 2089407 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0889. Min Act: -0.1700
Data Index: 5397946 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0889. Min Act: -0.1700
Data Index: 7096756 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0732. Min Act: -0.1700
Data Index: 5622678 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0576. Min Act: -0.1700
Data Index: 6742730 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2139. Min Range: -4.2139
Max Act: 4.0576. Min Act: -0.1700
Data Index: 6955749 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19