Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2286 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.8411. Min Act: -0.1700
Data Index: 939633 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.8068. Min Act: -0.1700
Data Index: 8214675 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7895. Min Act: -0.1700
Data Index: 950486 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7723. Min Act: -0.1700
Data Index: 6973615 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7637. Min Act: -0.1700
Data Index: 8118525 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7464. Min Act: -0.1700
Data Index: 4382482 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7464. Min Act: -0.1700
Data Index: 4494062 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7291. Min Act: -0.1700
Data Index: 2880545 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7378. Min Act: -0.1697
Data Index: 8128711 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7291. Min Act: -0.1700
Data Index: 2569753 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7378. Min Act: -0.1700
Data Index: 7058660 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7118. Min Act: -0.1699
Data Index: 2700782 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7118. Min Act: -0.1700
Data Index: 880314 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7118. Min Act: -0.1700
Data Index: 8574337 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7118. Min Act: -0.1700
Data Index: 4906442 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7031. Min Act: -0.1698
Data Index: 2097068 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7031. Min Act: -0.1700
Data Index: 6392676 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.6945. Min Act: -0.1700
Data Index: 1712800 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7031. Min Act: -0.1700
Data Index: 281682 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8411. Min Range: -1.8411
Max Act: 1.7031. Min Act: -0.1700
Data Index: 524613 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19