Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5049 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0303. Min Range: -5.0303
Max Act: 5.0303. Min Act: -0.1700
Data Index: 2730029 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0303. Min Range: -5.0303
Max Act: 5.0303. Min Act: -0.1700
Data Index: 7586406 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.9365. Min Act: -0.1700
Data Index: 2364845 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.6865. Min Act: -0.1700
Data Index: 1680559 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.6865. Min Act: -0.1700
Data Index: 830500 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.6240. Min Act: -0.1700
Data Index: 2094606 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.6553. Min Act: -0.1700
Data Index: 5452752 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.6553. Min Act: -0.1700
Data Index: 6985606 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.6553. Min Act: -0.1700
Data Index: 6392557 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5928. Min Act: -0.1700
Data Index: 4388935 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5928. Min Act: -0.1700
Data Index: 8125547 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5928. Min Act: -0.1700
Data Index: 3182504 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5928. Min Act: -0.1700
Data Index: 5486871 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5928. Min Act: -0.1700
Data Index: 530861 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5928. Min Act: -0.1700
Data Index: 8574571 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5615. Min Act: -0.1700
Data Index: 6993253 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5302. Min Act: -0.1700
Data Index: 5414810 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5615. Min Act: -0.1700
Data Index: 7876171 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5302. Min Act: -0.1700
Data Index: 4250290 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0303. Min Range: -5.0303
Max Act: 4.5615. Min Act: -0.1700
Data Index: 14374 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19