Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1539. Min Range: -6.1539
Max Act: 6.1539. Min Act: -0.1700
Data Index: 7749328 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.7789. Min Act: -0.1700
Data Index: 4847871 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.7789. Min Act: -0.1700
Data Index: 6964279 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.7476. Min Act: -0.1700
Data Index: 6462601 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.6851. Min Act: -0.1700
Data Index: 280521 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.6851. Min Act: -0.1700
Data Index: 4093885 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.6539. Min Act: -0.1700
Data Index: 2828024 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.6539. Min Act: -0.1700
Data Index: 354969 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.6539. Min Act: -0.1700
Data Index: 1352244 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.6226. Min Act: -0.1700
Data Index: 1704391 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5914. Min Act: -0.1700
Data Index: 5863165 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5914. Min Act: -0.1700
Data Index: 6458038 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5601. Min Act: -0.1700
Data Index: 4864475 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5601. Min Act: -0.1700
Data Index: 5428307 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5914. Min Act: -0.1700
Data Index: 321134 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5601. Min Act: -0.1700
Data Index: 4090848 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5601. Min Act: -0.1700
Data Index: 3295321 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5601. Min Act: -0.1700
Data Index: 2343779 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5601. Min Act: -0.1700
Data Index: 8502332 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1539. Min Range: -6.1539
Max Act: 5.5289. Min Act: -0.1700
Data Index: 4505356 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19