Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.3091. Min Act: -0.1700
Data Index: 2928295 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.2779. Min Act: -0.1700
Data Index: 7079227 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.1529. Min Act: -0.1700
Data Index: 3782934 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.1216. Min Act: -0.1700
Data Index: 4821168 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0904. Min Act: -0.1700
Data Index: 4914885 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0904. Min Act: -0.1700
Data Index: 710146 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0904. Min Act: -0.1700
Data Index: 924945 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0591. Min Act: -0.1700
Data Index: 5191 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0278. Min Act: -0.1700
Data Index: 1096722 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0278. Min Act: -0.1700
Data Index: 5189131 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0278. Min Act: -0.1700
Data Index: 527520 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0278. Min Act: -0.1700
Data Index: 924946 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3091. Min Range: -4.3091
Max Act: 4.0278. Min Act: -0.1700
Data Index: 799618 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3091. Min Range: -4.3091
Max Act: 3.9966. Min Act: -0.1700
Data Index: 5511654 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3091. Min Range: -4.3091
Max Act: 3.9653. Min Act: -0.1700
Data Index: 3393494 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3091. Min Range: -4.3091
Max Act: 3.9966. Min Act: -0.1700
Data Index: 4468260 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3091. Min Range: -4.3091
Max Act: 3.9966. Min Act: -0.1700
Data Index: 515723 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3091. Min Range: -4.3091
Max Act: 3.9653. Min Act: -0.1700
Data Index: 6929823 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3091. Min Range: -4.3091
Max Act: 3.9341. Min Act: -0.1700
Data Index: 2522228 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3091. Min Range: -4.3091
Max Act: 3.9653. Min Act: -0.1700
Data Index: 5313527 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19