Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.3352. Min Act: -0.1700
Data Index: 1179347 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.1165. Min Act: -0.1700
Data Index: 8813405 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.1165. Min Act: -0.1700
Data Index: 6638852 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.0852. Min Act: -0.1700
Data Index: 5282282 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.0540. Min Act: -0.1700
Data Index: 1252337 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.0540. Min Act: -0.1700
Data Index: 7112519 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.9915. Min Act: -0.1700
Data Index: 3686957 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3352. Min Range: -6.3352
Max Act: 6.0227. Min Act: -0.1700
Data Index: 7486268 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.9290. Min Act: -0.1700
Data Index: 3687666 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.9290. Min Act: -0.1700
Data Index: 7759522 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8665. Min Act: -0.1700
Data Index: 1936661 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8352. Min Act: -0.1700
Data Index: 8709815 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8040. Min Act: -0.1700
Data Index: 5341354 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8040. Min Act: -0.1700
Data Index: 4633570 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8352. Min Act: -0.1700
Data Index: 2380354 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8040. Min Act: -0.1700
Data Index: 2642815 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8040. Min Act: -0.1700
Data Index: 696350 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.8040. Min Act: -0.1700
Data Index: 4667041 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.7727. Min Act: -0.1700
Data Index: 23107 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3352. Min Range: -6.3352
Max Act: 5.7727. Min Act: -0.1700
Data Index: 6411808 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19