Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1924 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.7774. Min Act: -0.1700
Data Index: 863684 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.5899. Min Act: -0.1700
Data Index: 5122491 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.2149. Min Act: -0.1700
Data Index: 4663997 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7774. Min Range: -8.7774
Max Act: 7.4024. Min Act: -0.1700
Data Index: 3404925 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.3399. Min Act: -0.1700
Data Index: 1145525 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.2774. Min Act: -0.1699
Data Index: 5153038 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.0899. Min Act: -0.1700
Data Index: 3651078 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.1524. Min Act: -0.1700
Data Index: 3404910 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7774. Min Range: -8.7774
Max Act: 7.8399. Min Act: -0.1700
Data Index: 8090918 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.1524. Min Act: -0.1700
Data Index: 5743084 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7774. Min Range: -8.7774
Max Act: 7.6211. Min Act: -0.1700
Data Index: 2216053 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.5899. Min Act: -0.1700
Data Index: 3404914 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7774. Min Range: -8.7774
Max Act: 6.8399. Min Act: -0.1700
Data Index: 2207812 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.0899. Min Act: -0.1700
Data Index: 3404899 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7774. Min Range: -8.7774
Max Act: 7.7774. Min Act: -0.1700
Data Index: 5153029 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7774. Min Range: -8.7774
Max Act: 7.7149. Min Act: -0.1676
Data Index: 1455399 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7774. Min Range: -8.7774
Max Act: 7.4649. Min Act: -0.1700
Data Index: 6774810 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7774. Min Range: -8.7774
Max Act: 7.1211. Min Act: -0.1698
Data Index: 206636 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7774. Min Range: -8.7774
Max Act: 8.7774. Min Act: -0.1700
Data Index: 6071838 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7774. Min Range: -8.7774
Max Act: 7.5586. Min Act: -0.1700
Data Index: 937656 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19