Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.3896. Min Act: -0.1700
Data Index: 1204345 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1083. Min Act: -0.1700
Data Index: 4387204 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.0458. Min Act: -0.1700
Data Index: 5109844 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.0458. Min Act: -0.1700
Data Index: 4008943 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.0146. Min Act: -0.1700
Data Index: 3322803 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.0146. Min Act: -0.1700
Data Index: 3270383 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.9520. Min Act: -0.1700
Data Index: 1129657 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.9520. Min Act: -0.1700
Data Index: 3748699 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.9520. Min Act: -0.1700
Data Index: 5551140 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.9208. Min Act: -0.1700
Data Index: 5551137 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.9208. Min Act: -0.1700
Data Index: 2059154 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.8895. Min Act: -0.1700
Data Index: 2801406 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.8895. Min Act: -0.1700
Data Index: 3633820 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.8582. Min Act: -0.1700
Data Index: 4965270 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.8895. Min Act: -0.1700
Data Index: 1452502 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.8895. Min Act: -0.1700
Data Index: 7222369 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.8582. Min Act: -0.1700
Data Index: 5714479 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.9208. Min Act: -0.1700
Data Index: 6763486 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.8582. Min Act: -0.1700
Data Index: 13014 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3896. Min Range: -4.3896
Max Act: 3.8582. Min Act: -0.1700
Data Index: 3514668 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19