Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1448. Min Range: -5.1448
Max Act: 5.1448. Min Act: -0.1700
Data Index: 8681172 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9886. Min Act: -0.1700
Data Index: 2439226 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9886. Min Act: -0.1700
Data Index: 7767688 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9573. Min Act: -0.1700
Data Index: 3694757 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9261. Min Act: -0.1700
Data Index: 8681169 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9886. Min Act: -0.1700
Data Index: 7449146 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9573. Min Act: -0.1700
Data Index: 4374708 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9261. Min Act: -0.1700
Data Index: 6587835 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9573. Min Act: -0.1700
Data Index: 5862772 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8948. Min Act: -0.1700
Data Index: 3417092 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8636. Min Act: -0.1700
Data Index: 5414858 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8636. Min Act: -0.1700
Data Index: 911032 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8636. Min Act: -0.1700
Data Index: 3355106 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8323. Min Act: -0.1700
Data Index: 4207017 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8636. Min Act: -0.1700
Data Index: 701252 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8636. Min Act: -0.1700
Data Index: 3160072 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8323. Min Act: -0.1700
Data Index: 4992742 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9261. Min Act: -0.1700
Data Index: 7996299 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8011. Min Act: -0.1700
Data Index: 8470411 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8636. Min Act: -0.1700
Data Index: 155834 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19