Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1831 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.2730. Min Act: -0.1700
Data Index: 792252 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1167. Min Act: -0.1700
Data Index: 1358468 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0855. Min Act: -0.1700
Data Index: 4359263 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0542. Min Act: -0.1700
Data Index: 4336234 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0230. Min Act: -0.1700
Data Index: 6288733 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0230. Min Act: -0.1700
Data Index: 7384425 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0230. Min Act: -0.1700
Data Index: 7049399 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9605. Min Act: -0.1700
Data Index: 689685 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4245613 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9917. Min Act: -0.1700
Data Index: 937047 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9605. Min Act: -0.1700
Data Index: 1217538 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9605. Min Act: -0.1700
Data Index: 458701 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9292. Min Act: -0.1700
Data Index: 7843407 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.9605. Min Act: -0.1700
Data Index: 4471380 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.8980. Min Act: -0.1700
Data Index: 2663683 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.8667. Min Act: -0.1700
Data Index: 7069284 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.8667. Min Act: -0.1700
Data Index: 6333150 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.8667. Min Act: -0.1700
Data Index: 1743069 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.8355. Min Act: -0.1700
Data Index: 7716860 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2730. Min Range: -5.2730
Max Act: 4.8355. Min Act: -0.1700
Data Index: 2587077 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19