Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3219. Min Range: -6.3219
Max Act: 6.3219. Min Act: -0.1700
Data Index: 567142 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3219. Min Range: -6.3219
Max Act: 6.1344. Min Act: -0.1700
Data Index: 4120087 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3219. Min Range: -6.3219
Max Act: 6.0719. Min Act: -0.1700
Data Index: 3417353 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3219. Min Range: -6.3219
Max Act: 6.0094. Min Act: -0.1700
Data Index: 3337878 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.9781. Min Act: -0.1700
Data Index: 2740388 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.9781. Min Act: -0.1700
Data Index: 3342287 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.8844. Min Act: -0.1700
Data Index: 4568632 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.8844. Min Act: -0.1700
Data Index: 5421084 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.8219. Min Act: -0.1700
Data Index: 1519207 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.8531. Min Act: -0.1700
Data Index: 3254603 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.8531. Min Act: -0.1700
Data Index: 4691611 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.8219. Min Act: -0.1700
Data Index: 3788269 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.7594. Min Act: -0.1700
Data Index: 6589325 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.7594. Min Act: -0.1700
Data Index: 5351988 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.7594. Min Act: -0.1700
Data Index: 2650053 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.7594. Min Act: -0.1700
Data Index: 8650047 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.8219. Min Act: -0.1700
Data Index: 8299685 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.7594. Min Act: -0.1700
Data Index: 6358918 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.7281. Min Act: -0.1700
Data Index: 6694604 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3219. Min Range: -6.3219
Max Act: 5.7281. Min Act: -0.1700
Data Index: 7668912 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19