Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.9383. Min Act: -0.1700
Data Index: 8636383 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.9225. Min Act: -0.1700
Data Index: 6176016 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.8273. Min Act: -0.1700
Data Index: 7209600 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.8114. Min Act: -0.1700
Data Index: 2490147 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.8114. Min Act: -0.1700
Data Index: 4113964 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.8114. Min Act: -0.1700
Data Index: 918580 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7954. Min Act: -0.1700
Data Index: 5525675 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7795. Min Act: -0.1700
Data Index: 2358639 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7795. Min Act: -0.1700
Data Index: 1953046 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7795. Min Act: -0.1700
Data Index: 7656346 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7636. Min Act: -0.1700
Data Index: 1182062 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7636. Min Act: -0.1700
Data Index: 7289780 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7636. Min Act: -0.1700
Data Index: 7405993 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7636. Min Act: -0.1700
Data Index: 7553759 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7476. Min Act: -0.1700
Data Index: 266278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7476. Min Act: -0.1700
Data Index: 3137722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7476. Min Act: -0.1700
Data Index: 4255101 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7476. Min Act: -0.1700
Data Index: 957985 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7476. Min Act: -0.1700
Data Index: 5565138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9383. Min Range: -2.9383
Max Act: 2.7316. Min Act: -0.1700
Data Index: 8468581 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19