Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4591 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.5518. Min Act: -0.1700
Data Index: 2399095 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.4268. Min Act: -0.1700
Data Index: 7118505 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.4268. Min Act: -0.1700
Data Index: 8019349 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.3955. Min Act: -0.1700
Data Index: 7809434 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.3330. Min Act: -0.1700
Data Index: 7118506 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.2705. Min Act: -0.1700
Data Index: 8132221 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.2080. Min Act: -0.1700
Data Index: 2926528 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.2080. Min Act: -0.1700
Data Index: 2926529 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.1143. Min Act: -0.1700
Data Index: 8545656 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.0830. Min Act: -0.1700
Data Index: 6393732 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.0518. Min Act: -0.1700
Data Index: 6393731 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5518. Min Range: -6.5518
Max Act: 6.0205. Min Act: -0.1700
Data Index: 4266591 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5518. Min Range: -6.5518
Max Act: 5.9893. Min Act: -0.1700
Data Index: 3221098 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5518. Min Range: -6.5518
Max Act: 5.9580. Min Act: -0.1700
Data Index: 1149570 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5518. Min Range: -6.5518
Max Act: 5.9580. Min Act: -0.1700
Data Index: 803737 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5518. Min Range: -6.5518
Max Act: 5.9580. Min Act: -0.1700
Data Index: 4584178 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5518. Min Range: -6.5518
Max Act: 5.9580. Min Act: -0.1700
Data Index: 8145328 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5518. Min Range: -6.5518
Max Act: 5.9268. Min Act: -0.1700
Data Index: 4541347 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5518. Min Range: -6.5518
Max Act: 5.9268. Min Act: -0.1700
Data Index: 5691460 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5518. Min Range: -6.5518
Max Act: 5.9268. Min Act: -0.1700
Data Index: 5742771 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19