Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.8384. Min Act: -0.1700
Data Index: 7885522 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.7446. Min Act: -0.1700
Data Index: 690438 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.6821. Min Act: -0.1700
Data Index: 2932127 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.6509. Min Act: -0.1700
Data Index: 4041812 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.6196. Min Act: -0.1700
Data Index: 4802106 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.5259. Min Act: -0.1700
Data Index: 2049663 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.5259. Min Act: -0.1700
Data Index: 6889857 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.5259. Min Act: -0.1700
Data Index: 3741761 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.4634. Min Act: -0.1700
Data Index: 1427268 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.4634. Min Act: -0.1700
Data Index: 289924 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.4321. Min Act: -0.1700
Data Index: 1614613 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.4009. Min Act: -0.1700
Data Index: 8110899 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.4009. Min Act: -0.1700
Data Index: 4146527 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.3696. Min Act: -0.1700
Data Index: 8771220 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.2759. Min Act: -0.1700
Data Index: 5878121 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.3071. Min Act: -0.1700
Data Index: 4720704 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.3071. Min Act: -0.1700
Data Index: 8646403 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.3071. Min Act: -0.1700
Data Index: 2928618 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.3071. Min Act: -0.1700
Data Index: 3907963 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8384. Min Range: -6.8384
Max Act: 6.2759. Min Act: -0.1700
Data Index: 4579700 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19