Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0835. Min Range: -8.0835
Max Act: 8.0835. Min Act: -0.1700
Data Index: 6466400 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.7710. Min Act: -0.1700
Data Index: 5862539 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.7398. Min Act: -0.1700
Data Index: 5291953 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.7398. Min Act: -0.1700
Data Index: 7947652 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.6460. Min Act: -0.1700
Data Index: 4866754 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.6460. Min Act: -0.1700
Data Index: 806579 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.5835. Min Act: -0.1700
Data Index: 2576923 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.6773. Min Act: -0.1700
Data Index: 8204277 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.6148. Min Act: -0.1700
Data Index: 4816756 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.5835. Min Act: -0.1700
Data Index: 5893432 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.6148. Min Act: -0.1700
Data Index: 3730101 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.5523. Min Act: -0.1700
Data Index: 7742536 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.4898. Min Act: -0.1700
Data Index: 1027961 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.4898. Min Act: -0.1700
Data Index: 8601994 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.5210. Min Act: -0.1700
Data Index: 952607 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.4585. Min Act: -0.1700
Data Index: 4861845 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.4585. Min Act: -0.1700
Data Index: 5153438 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.4585. Min Act: -0.1700
Data Index: 7304263 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.4898. Min Act: -0.1700
Data Index: 1434185 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0835. Min Range: -8.0835
Max Act: 7.4898. Min Act: -0.1700
Data Index: 4578979 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19