Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1347 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.6949. Min Act: -0.1700
Data Index: 8805292 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.6949. Min Act: -0.1700
Data Index: 4987720 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.6012. Min Act: -0.1700
Data Index: 8382785 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.6637. Min Act: -0.1700
Data Index: 4987719 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.6012. Min Act: -0.1700
Data Index: 3371566 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.6012. Min Act: -0.1700
Data Index: 8272754 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5699. Min Act: -0.1700
Data Index: 8557486 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5699. Min Act: -0.1700
Data Index: 2168401 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5387. Min Act: -0.1700
Data Index: 817106 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5699. Min Act: -0.1700
Data Index: 2097194 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.6012. Min Act: -0.1700
Data Index: 5143212 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5699. Min Act: -0.1700
Data Index: 7689934 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5387. Min Act: -0.1700
Data Index: 5775728 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5387. Min Act: -0.1700
Data Index: 411072 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5387. Min Act: -0.1700
Data Index: 248641 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5387. Min Act: -0.1700
Data Index: 6270587 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5074. Min Act: -0.1700
Data Index: 4987721 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5074. Min Act: -0.1700
Data Index: 4987722 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.5074. Min Act: -0.1700
Data Index: 5995851 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6949. Min Range: -4.6949
Max Act: 4.4762. Min Act: -0.1700
Data Index: 3410962 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19