Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6145 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1804. Min Range: -6.1804
Max Act: 6.1804. Min Act: -0.1700
Data Index: 536663 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.9616. Min Act: -0.1700
Data Index: 5923925 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.8366. Min Act: -0.1700
Data Index: 8341982 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.7429. Min Act: -0.1700
Data Index: 808817 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.7429. Min Act: -0.1700
Data Index: 7212656 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.7741. Min Act: -0.1700
Data Index: 4410044 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6804. Min Act: -0.1700
Data Index: 1484794 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6804. Min Act: -0.1700
Data Index: 6176160 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6491. Min Act: -0.1700
Data Index: 1989391 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6491. Min Act: -0.1700
Data Index: 7296307 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6491. Min Act: -0.1700
Data Index: 384334 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6179. Min Act: -0.1700
Data Index: 2485942 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6179. Min Act: -0.1700
Data Index: 4799101 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6179. Min Act: -0.1700
Data Index: 6301592 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6179. Min Act: -0.1700
Data Index: 6104007 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.6179. Min Act: -0.1700
Data Index: 2523766 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.5866. Min Act: -0.1700
Data Index: 7570378 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.5554. Min Act: -0.1700
Data Index: 2881557 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.5866. Min Act: -0.1700
Data Index: 4869536 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1804. Min Range: -6.1804
Max Act: 5.5866. Min Act: -0.1700
Data Index: 5340533 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19