Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0969. Min Range: -6.0969
Max Act: 6.0969. Min Act: -0.1700
Data Index: 6185028 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.9406. Min Act: -0.1700
Data Index: 3134290 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.8469. Min Act: -0.1700
Data Index: 4094295 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.8469. Min Act: -0.1700
Data Index: 5966219 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.8156. Min Act: -0.1700
Data Index: 6511952 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.8156. Min Act: -0.1700
Data Index: 525913 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.6906. Min Act: -0.1700
Data Index: 3215526 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.6594. Min Act: -0.1700
Data Index: 1517914 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.6594. Min Act: -0.1700
Data Index: 5213219 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.6281. Min Act: -0.1700
Data Index: 497649 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5969. Min Act: -0.1700
Data Index: 4311581 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5969. Min Act: -0.1700
Data Index: 3433844 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5656. Min Act: -0.1700
Data Index: 1715543 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5969. Min Act: -0.1700
Data Index: 4853118 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5969. Min Act: -0.1700
Data Index: 4119147 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5969. Min Act: -0.1700
Data Index: 7641646 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5656. Min Act: -0.1700
Data Index: 5371558 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5656. Min Act: -0.1700
Data Index: 4314036 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5031. Min Act: -0.1700
Data Index: 4565675 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0969. Min Range: -6.0969
Max Act: 5.5344. Min Act: -0.1700
Data Index: 3112060 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19