Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1634 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.4710. Min Act: -0.1700
Data Index: 7563260 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.4398. Min Act: -0.1700
Data Index: 3313749 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.3773. Min Act: -0.1700
Data Index: 7732672 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.4085. Min Act: -0.1700
Data Index: 1056140 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.3148. Min Act: -0.1700
Data Index: 4448713 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.2835. Min Act: -0.1700
Data Index: 66507 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.3148. Min Act: -0.1700
Data Index: 7771470 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.2523. Min Act: -0.1700
Data Index: 7167599 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.2523. Min Act: -0.1700
Data Index: 5336468 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.3148. Min Act: -0.1700
Data Index: 3183160 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1898. Min Act: -0.1700
Data Index: 7984231 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1585. Min Act: -0.1700
Data Index: 5141832 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1585. Min Act: -0.1700
Data Index: 3479528 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1898. Min Act: -0.1700
Data Index: 7925603 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1898. Min Act: -0.1700
Data Index: 646450 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1273. Min Act: -0.1700
Data Index: 2626897 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1273. Min Act: -0.1700
Data Index: 6122617 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1273. Min Act: -0.1700
Data Index: 7060631 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1898. Min Act: -0.1700
Data Index: 1729639 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4710. Min Range: -6.4710
Max Act: 6.1585. Min Act: -0.1700
Data Index: 4925949 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19