Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0164. Min Range: -3.0164
Max Act: 3.0164. Min Act: -0.1700
Data Index: 2607791 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.9690. Min Act: -0.1700
Data Index: 1962916 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.9373. Min Act: -0.1700
Data Index: 2796271 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.9215. Min Act: -0.1700
Data Index: 6155509 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.8739. Min Act: -0.1700
Data Index: 7541068 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.8421. Min Act: -0.1700
Data Index: 1082931 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.8421. Min Act: -0.1700
Data Index: 6453060 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.8421. Min Act: -0.1700
Data Index: 3201377 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.8262. Min Act: -0.1700
Data Index: 1145565 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7944. Min Act: -0.1700
Data Index: 7907117 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.8103. Min Act: -0.1700
Data Index: 5741149 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7944. Min Act: -0.1700
Data Index: 3736066 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7944. Min Act: -0.1700
Data Index: 4308435 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7625. Min Act: -0.1700
Data Index: 2853110 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7466. Min Act: -0.1700
Data Index: 7303533 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7466. Min Act: -0.1700
Data Index: 1425292 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7146. Min Act: -0.1700
Data Index: 2645159 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.6986. Min Act: -0.1700
Data Index: 1994911 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7146. Min Act: -0.1700
Data Index: 7343006 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0164. Min Range: -3.0164
Max Act: 2.7306. Min Act: -0.1700
Data Index: 2142223 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19