Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.4395. Min Act: -0.1700
Data Index: 752294 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.1895. Min Act: -0.1700
Data Index: 6193737 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.0957. Min Act: -0.1700
Data Index: 2932898 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.1270. Min Act: -0.1700
Data Index: 2394400 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.0645. Min Act: -0.1700
Data Index: 6109874 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.0645. Min Act: -0.1700
Data Index: 5965862 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.0332. Min Act: -0.1700
Data Index: 6797087 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.0020. Min Act: -0.1700
Data Index: 7908254 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.0020. Min Act: -0.1700
Data Index: 8711535 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9707. Min Act: -0.1700
Data Index: 8715009 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4395. Min Range: -5.4395
Max Act: 5.0332. Min Act: -0.1700
Data Index: 1342743 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9707. Min Act: -0.1700
Data Index: 1995460 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9707. Min Act: -0.1700
Data Index: 6023189 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9707. Min Act: -0.1700
Data Index: 3002443 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9707. Min Act: -0.1700
Data Index: 7187190 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9707. Min Act: -0.1700
Data Index: 4886474 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9082. Min Act: -0.1700
Data Index: 8231178 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9395. Min Act: -0.1700
Data Index: 8186539 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9395. Min Act: -0.1700
Data Index: 8576780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4395. Min Range: -5.4395
Max Act: 4.9395. Min Act: -0.1700
Data Index: 147751 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19