Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0046. Min Range: -6.0046
Max Act: 6.0046. Min Act: -0.1700
Data Index: 8364211 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.9734. Min Act: -0.1700
Data Index: 1631525 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.8796. Min Act: -0.1700
Data Index: 7636402 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.8171. Min Act: -0.1700
Data Index: 4706842 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.7546. Min Act: -0.1700
Data Index: 2455480 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.6609. Min Act: -0.1700
Data Index: 3092461 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.6296. Min Act: -0.1700
Data Index: 261651 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.6609. Min Act: -0.1700
Data Index: 2736741 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5984. Min Act: -0.1700
Data Index: 2524340 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5046. Min Act: -0.1700
Data Index: 7912702 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5046. Min Act: -0.1700
Data Index: 4646722 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5046. Min Act: -0.1700
Data Index: 7621913 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5359. Min Act: -0.1700
Data Index: 4834638 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5671. Min Act: -0.1700
Data Index: 3785301 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5046. Min Act: -0.1700
Data Index: 7779174 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5046. Min Act: -0.1700
Data Index: 2634209 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.4734. Min Act: -0.1700
Data Index: 6950293 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.5046. Min Act: -0.1700
Data Index: 6852474 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.4734. Min Act: -0.1700
Data Index: 7548644 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0046. Min Range: -6.0046
Max Act: 5.4734. Min Act: -0.1700
Data Index: 6601133 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19