Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 725 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4363. Min Act: -0.1700
Data Index: 4903707 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4050. Min Act: -0.1700
Data Index: 920607 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3425. Min Act: -0.1700
Data Index: 3728218 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2800. Min Act: -0.1700
Data Index: 7103833 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 412853 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 2385934 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 1021843 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 64450 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2175. Min Act: -0.1700
Data Index: 7978889 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2175. Min Act: -0.1700
Data Index: 7269977 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 550354 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 2506716 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2175. Min Act: -0.1700
Data Index: 811057 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 40072 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1550. Min Act: -0.1700
Data Index: 8552650 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 533561 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1863. Min Act: -0.1700
Data Index: 2402024 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1238. Min Act: -0.1700
Data Index: 2092357 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1550. Min Act: -0.1700
Data Index: 4426443 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.1238. Min Act: -0.1700
Data Index: 2451130 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19