Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2467 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.7623. Min Act: -0.1700
Data Index: 3971657 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.6373. Min Act: -0.1700
Data Index: 2280648 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.5123. Min Act: -0.1700
Data Index: 3479892 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.4186. Min Act: -0.1700
Data Index: 5472066 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.3248. Min Act: -0.1700
Data Index: 3734648 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.2936. Min Act: -0.1700
Data Index: 660 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.2623. Min Act: -0.1700
Data Index: 6091851 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.2311. Min Act: -0.1700
Data Index: 5967618 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.2623. Min Act: -0.1700
Data Index: 4153438 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.2311. Min Act: -0.1700
Data Index: 2443798 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1998. Min Act: -0.1700
Data Index: 2195303 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1686. Min Act: -0.1700
Data Index: 7427852 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1998. Min Act: -0.1700
Data Index: 5109368 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1998. Min Act: -0.1700
Data Index: 3154366 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1686. Min Act: -0.1700
Data Index: 6721326 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1373. Min Act: -0.1700
Data Index: 3955449 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1373. Min Act: -0.1700
Data Index: 6022381 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1373. Min Act: -0.1700
Data Index: 7262379 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.1373. Min Act: -0.1700
Data Index: 2082343 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7623. Min Range: -6.7623
Max Act: 6.0748. Min Act: -0.1700
Data Index: 4091635 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19