Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 317 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.9676. Min Act: -0.1700
Data Index: 2891191 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.5614. Min Act: -0.1700
Data Index: 7579437 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.5301. Min Act: -0.1700
Data Index: 514474 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.4364. Min Act: -0.1700
Data Index: 900559 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.2489. Min Act: -0.1700
Data Index: 8211876 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1864. Min Act: -0.1700
Data Index: 5041747 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1551. Min Act: -0.1700
Data Index: 4915499 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1864. Min Act: -0.1700
Data Index: 5859903 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1864. Min Act: -0.1700
Data Index: 6863769 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1864. Min Act: -0.1700
Data Index: 2001358 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1864. Min Act: -0.1700
Data Index: 5852922 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1551. Min Act: -0.1700
Data Index: 1973591 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1551. Min Act: -0.1700
Data Index: 7418587 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1551. Min Act: -0.1700
Data Index: 5272723 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1551. Min Act: -0.1700
Data Index: 51442 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1239. Min Act: -0.1700
Data Index: 4962660 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1239. Min Act: -0.1700
Data Index: 2348290 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1239. Min Act: -0.1700
Data Index: 2025529 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.1551. Min Act: -0.1700
Data Index: 3859979 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9676. Min Range: -6.9676
Max Act: 6.0926. Min Act: -0.1700
Data Index: 7908076 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19