Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.3386. Min Act: -0.1700
Data Index: 8806430 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.2448. Min Act: -0.1700
Data Index: 8522055 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.2448. Min Act: -0.1700
Data Index: 8398034 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.2136. Min Act: -0.1700
Data Index: 6278678 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.2136. Min Act: -0.1700
Data Index: 8210538 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.1823. Min Act: -0.1700
Data Index: 5589695 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.1511. Min Act: -0.1700
Data Index: 5989961 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.1198. Min Act: -0.1700
Data Index: 7184398 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.1823. Min Act: -0.1700
Data Index: 2295441 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.1198. Min Act: -0.1700
Data Index: 5742246 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0886. Min Act: -0.1700
Data Index: 115790 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0886. Min Act: -0.1700
Data Index: 3213584 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0886. Min Act: -0.1700
Data Index: 959241 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0886. Min Act: -0.1700
Data Index: 1903768 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0573. Min Act: -0.1700
Data Index: 5695221 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0573. Min Act: -0.1700
Data Index: 3886516 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0573. Min Act: -0.1700
Data Index: 8716 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0573. Min Act: -0.1700
Data Index: 8311257 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0573. Min Act: -0.1700
Data Index: 1699776 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3386. Min Range: -4.3386
Max Act: 4.0573. Min Act: -0.1700
Data Index: 5289527 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19