Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3486. Min Range: -7.3486
Max Act: 7.3486. Min Act: -0.1700
Data Index: 4344278 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.7861. Min Act: -0.1700
Data Index: 2884933 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.7549. Min Act: -0.1700
Data Index: 6233526 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.7549. Min Act: -0.1700
Data Index: 7649357 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.7236. Min Act: -0.1700
Data Index: 5838626 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.5986. Min Act: -0.1700
Data Index: 1214590 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.5986. Min Act: -0.1700
Data Index: 695886 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.5049. Min Act: -0.1700
Data Index: 4003687 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.5361. Min Act: -0.1700
Data Index: 6297813 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.4424. Min Act: -0.1700
Data Index: 2315835 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.4424. Min Act: -0.1700
Data Index: 6480533 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.4111. Min Act: -0.1700
Data Index: 2297856 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.3799. Min Act: -0.1700
Data Index: 5487107 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.4111. Min Act: -0.1700
Data Index: 6919968 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.3799. Min Act: -0.1700
Data Index: 2196663 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.3799. Min Act: -0.1700
Data Index: 8461801 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.3486. Min Act: -0.1700
Data Index: 5171473 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.3174. Min Act: -0.1700
Data Index: 7054403 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.3486. Min Act: -0.1700
Data Index: 159721 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3486. Min Range: -7.3486
Max Act: 6.3174. Min Act: -0.1700
Data Index: 503499 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19