Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4723 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1235. Min Range: -7.1235
Max Act: 7.1235. Min Act: -0.1700
Data Index: 1312381 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1235. Min Range: -7.1235
Max Act: 7.0298. Min Act: -0.1700
Data Index: 8058582 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.9985. Min Act: -0.1700
Data Index: 7961790 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.9673. Min Act: -0.1700
Data Index: 3978337 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.7173. Min Act: -0.1700
Data Index: 5331802 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6860. Min Act: -0.1700
Data Index: 6190633 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6860. Min Act: -0.1700
Data Index: 6008331 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6548. Min Act: -0.1700
Data Index: 3020791 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6548. Min Act: -0.1700
Data Index: 2106345 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5923. Min Act: -0.1700
Data Index: 3386958 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5923. Min Act: -0.1700
Data Index: 7017808 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5298. Min Act: -0.1700
Data Index: 8780098 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5610. Min Act: -0.1700
Data Index: 173974 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5298. Min Act: -0.1700
Data Index: 1155224 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5298. Min Act: -0.1700
Data Index: 545586 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.4985. Min Act: -0.1700
Data Index: 7315612 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.4673. Min Act: -0.1700
Data Index: 3823341 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.4985. Min Act: -0.1700
Data Index: 2491244 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.4673. Min Act: -0.1700
Data Index: 5223196 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.4360. Min Act: -0.1700
Data Index: 4174732 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19