Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2898. Min Range: -6.2898
Max Act: 6.2898. Min Act: -0.1700
Data Index: 517924 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.9460. Min Act: -0.1700
Data Index: 2080754 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.8835. Min Act: -0.1700
Data Index: 326506 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.8523. Min Act: -0.1700
Data Index: 6742962 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.8210. Min Act: -0.1700
Data Index: 8818764 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.7585. Min Act: -0.1700
Data Index: 1048486 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6960. Min Act: -0.1700
Data Index: 6421876 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6960. Min Act: -0.1700
Data Index: 5340015 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6960. Min Act: -0.1700
Data Index: 7217936 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6648. Min Act: -0.1700
Data Index: 1278772 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6648. Min Act: -0.1700
Data Index: 1248613 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6960. Min Act: -0.1700
Data Index: 136505 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6335. Min Act: -0.1700
Data Index: 6592079 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6023. Min Act: -0.1700
Data Index: 2980264 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6335. Min Act: -0.1700
Data Index: 1313551 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6648. Min Act: -0.1700
Data Index: 3279236 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6335. Min Act: -0.1700
Data Index: 3997901 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6335. Min Act: -0.1700
Data Index: 6437572 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6335. Min Act: -0.1700
Data Index: 5448300 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2898. Min Range: -6.2898
Max Act: 5.6335. Min Act: -0.1700
Data Index: 7800696 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19