Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5739 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1398. Min Range: -7.1398
Max Act: 7.1398. Min Act: -0.1700
Data Index: 8465759 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1398. Min Range: -7.1398
Max Act: 7.0773. Min Act: -0.1700
Data Index: 8465758 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.8585. Min Act: -0.1700
Data Index: 4483399 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.8585. Min Act: -0.1700
Data Index: 7763215 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.8273. Min Act: -0.1700
Data Index: 4483397 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.8273. Min Act: -0.1700
Data Index: 4355051 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.8273. Min Act: -0.1700
Data Index: 7700233 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7960. Min Act: -0.1700
Data Index: 900531 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7648. Min Act: -0.1700
Data Index: 1374240 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7335. Min Act: -0.1700
Data Index: 2800714 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7648. Min Act: -0.1700
Data Index: 7256482 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7335. Min Act: -0.1700
Data Index: 8205992 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7335. Min Act: -0.1700
Data Index: 506048 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7023. Min Act: -0.1700
Data Index: 6134173 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.6710. Min Act: -0.1700
Data Index: 5617764 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7023. Min Act: -0.1700
Data Index: 6484783 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7023. Min Act: -0.1700
Data Index: 419977 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.7023. Min Act: -0.1700
Data Index: 3595739 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.6710. Min Act: -0.1700
Data Index: 266070 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1398. Min Range: -7.1398
Max Act: 6.6710. Min Act: -0.1700
Data Index: 4485814 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19