Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.5655. Min Act: -0.1700
Data Index: 501845 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.4717. Min Act: -0.1700
Data Index: 182207 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.3780. Min Act: -0.1700
Data Index: 5409512 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.4092. Min Act: -0.1700
Data Index: 8744991 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.3155. Min Act: -0.1700
Data Index: 6551601 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.3155. Min Act: -0.1700
Data Index: 3417490 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.2842. Min Act: -0.1700
Data Index: 326664 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.2530. Min Act: -0.1700
Data Index: 4697297 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.2217. Min Act: -0.1700
Data Index: 5248318 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.2217. Min Act: -0.1700
Data Index: 3752782 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.2217. Min Act: -0.1700
Data Index: 502198 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1905. Min Act: -0.1700
Data Index: 5108094 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1905. Min Act: -0.1700
Data Index: 7722507 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1905. Min Act: -0.1700
Data Index: 4398617 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1905. Min Act: -0.1700
Data Index: 7512342 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1905. Min Act: -0.1700
Data Index: 8070130 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1592. Min Act: -0.1700
Data Index: 2230063 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1592. Min Act: -0.1700
Data Index: 6676782 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1592. Min Act: -0.1700
Data Index: 3849624 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5655. Min Range: -6.5655
Max Act: 6.1592. Min Act: -0.1700
Data Index: 1387085 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19