Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4210 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.3500. Min Act: -0.1700
Data Index: 1282430 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2843. Min Act: -0.1700
Data Index: 3177549 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.3007. Min Act: -0.1700
Data Index: 401859 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2678. Min Act: -0.1700
Data Index: 702060 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2678. Min Act: -0.1700
Data Index: 1598561 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2843. Min Act: -0.1700
Data Index: 8299304 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2513. Min Act: -0.1700
Data Index: 145509 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2513. Min Act: -0.1700
Data Index: 6639432 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2513. Min Act: -0.1700
Data Index: 1386237 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2513. Min Act: -0.1700
Data Index: 451005 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2182. Min Act: -0.1700
Data Index: 955242 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2182. Min Act: -0.1700
Data Index: 4738728 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2182. Min Act: -0.1700
Data Index: 4918897 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2182. Min Act: -0.1700
Data Index: 4078949 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2182. Min Act: -0.1700
Data Index: 832460 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2182. Min Act: -0.1700
Data Index: 2981317 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2016. Min Act: -0.1700
Data Index: 319494 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.1850. Min Act: -0.1700
Data Index: 7802412 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2016. Min Act: -0.1700
Data Index: 8044483 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3500. Min Range: -2.3500
Max Act: 2.2016. Min Act: -0.1700
Data Index: 2298404 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19