Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1916. Min Range: -6.1916
Max Act: 6.1916. Min Act: -0.1700
Data Index: 5486424 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1916. Min Range: -6.1916
Max Act: 6.0041. Min Act: -0.1700
Data Index: 1337249 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.9728. Min Act: -0.1700
Data Index: 4013326 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.9416. Min Act: -0.1700
Data Index: 2332798 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.9103. Min Act: -0.1700
Data Index: 2206714 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.9103. Min Act: -0.1700
Data Index: 8195503 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.8791. Min Act: -0.1700
Data Index: 175117 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.8166. Min Act: -0.1700
Data Index: 3936122 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.8166. Min Act: -0.1700
Data Index: 5037658 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.8166. Min Act: -0.1700
Data Index: 3617735 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7853. Min Act: -0.1700
Data Index: 4274115 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7853. Min Act: -0.1700
Data Index: 71402 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7541. Min Act: -0.1700
Data Index: 8088983 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7541. Min Act: -0.1700
Data Index: 7857465 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7541. Min Act: -0.1700
Data Index: 7687327 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2823862 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7228. Min Act: -0.1700
Data Index: 529350 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7228. Min Act: -0.1700
Data Index: 6693015 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7228. Min Act: -0.1700
Data Index: 3721015 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1916. Min Range: -6.1916
Max Act: 5.7228. Min Act: -0.1700
Data Index: 6265870 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19