Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 439 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.8568. Min Act: -0.1700
Data Index: 6867524 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.7630. Min Act: -0.1700
Data Index: 4662279 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2013917 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.6068. Min Act: -0.1700
Data Index: 3803827 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.5130. Min Act: -0.1700
Data Index: 5155850 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.5130. Min Act: -0.1700
Data Index: 7322982 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4505. Min Act: -0.1700
Data Index: 1135598 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4505. Min Act: -0.1700
Data Index: 5887354 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4193. Min Act: -0.1700
Data Index: 2207622 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3568. Min Act: -0.1700
Data Index: 6075429 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3880. Min Act: -0.1700
Data Index: 7400595 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3880. Min Act: -0.1700
Data Index: 672681 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3880. Min Act: -0.1700
Data Index: 2238602 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3568. Min Act: -0.1700
Data Index: 8301283 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3255. Min Act: -0.1700
Data Index: 2016469 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3255. Min Act: -0.1700
Data Index: 8612880 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3255. Min Act: -0.1700
Data Index: 5552617 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3255. Min Act: -0.1700
Data Index: 3170434 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.2943. Min Act: -0.1700
Data Index: 5555636 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.2630. Min Act: -0.1700
Data Index: 3723657 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19