Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 568 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2084. Min Range: -7.2084
Max Act: 7.2084. Min Act: -0.1700
Data Index: 2504615 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2084. Min Range: -7.2084
Max Act: 7.2084. Min Act: -0.1700
Data Index: 3519483 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2084. Min Range: -7.2084
Max Act: 7.0522. Min Act: -0.1700
Data Index: 2880370 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2084. Min Range: -7.2084
Max Act: 7.0209. Min Act: -0.1700
Data Index: 4508334 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.9897. Min Act: -0.1700
Data Index: 4550540 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.8959. Min Act: -0.1700
Data Index: 2670801 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.8647. Min Act: -0.1700
Data Index: 4545588 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.8022. Min Act: -0.1700
Data Index: 1888693 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.8022. Min Act: -0.1700
Data Index: 4843179 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.7397. Min Act: -0.1700
Data Index: 2504611 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.7084. Min Act: -0.1700
Data Index: 6296087 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.7084. Min Act: -0.1700
Data Index: 1148682 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.7084. Min Act: -0.1700
Data Index: 1879319 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.6772. Min Act: -0.1700
Data Index: 98306 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.6772. Min Act: -0.1700
Data Index: 2244459 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.6459. Min Act: -0.1700
Data Index: 6042770 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.6459. Min Act: -0.1700
Data Index: 998303 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.6459. Min Act: -0.1700
Data Index: 3987086 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.6147. Min Act: -0.1700
Data Index: 4821777 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2084. Min Range: -7.2084
Max Act: 6.5522. Min Act: -0.1700
Data Index: 3503623 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19