Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5626 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.1439. Min Act: -0.1700
Data Index: 3605624 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.1439. Min Act: -0.1700
Data Index: 78073 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.1126. Min Act: -0.1700
Data Index: 373707 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.1126. Min Act: -0.1700
Data Index: 4387123 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0814. Min Act: -0.1700
Data Index: 22292 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0501. Min Act: -0.1700
Data Index: 3411555 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0501. Min Act: -0.1700
Data Index: 7494309 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0501. Min Act: -0.1700
Data Index: 4263713 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0501. Min Act: -0.1700
Data Index: 2929984 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0189. Min Act: -0.1700
Data Index: 8228693 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0189. Min Act: -0.1700
Data Index: 7816052 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0189. Min Act: -0.1700
Data Index: 4935970 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1439. Min Range: -5.1439
Max Act: 4.9876. Min Act: -0.1700
Data Index: 6885709 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1439. Min Range: -5.1439
Max Act: 5.0189. Min Act: -0.1700
Data Index: 3682217 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1439. Min Range: -5.1439
Max Act: 4.9876. Min Act: -0.1700
Data Index: 555682 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1439. Min Range: -5.1439
Max Act: 4.9876. Min Act: -0.1700
Data Index: 4893838 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1439. Min Range: -5.1439
Max Act: 4.9876. Min Act: -0.1700
Data Index: 2375465 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1439. Min Range: -5.1439
Max Act: 4.9564. Min Act: -0.1700
Data Index: 6471847 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1439. Min Range: -5.1439
Max Act: 4.9251. Min Act: -0.1700
Data Index: 7357783 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1439. Min Range: -5.1439
Max Act: 4.9251. Min Act: -0.1700
Data Index: 846007 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19