Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3907 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.5966. Min Act: -0.1700
Data Index: 8790946 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.5966. Min Act: -0.1700
Data Index: 4905759 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.5029. Min Act: -0.1700
Data Index: 7612412 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.4091. Min Act: -0.1700
Data Index: 71625 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.3779. Min Act: -0.1700
Data Index: 2343738 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.3466. Min Act: -0.1700
Data Index: 6116265 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.3466. Min Act: -0.1700
Data Index: 7215736 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.3466. Min Act: -0.1700
Data Index: 4375640 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.2841. Min Act: -0.1700
Data Index: 8503908 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.2529. Min Act: -0.1700
Data Index: 8341247 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.2529. Min Act: -0.1700
Data Index: 8420316 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.2216. Min Act: -0.1700
Data Index: 7872199 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.2216. Min Act: -0.1700
Data Index: 2173121 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.2216. Min Act: -0.1700
Data Index: 1738022 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.1904. Min Act: -0.1700
Data Index: 7704343 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.1904. Min Act: -0.1700
Data Index: 3340437 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.1591. Min Act: -0.1700
Data Index: 1536730 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.1591. Min Act: -0.1700
Data Index: 3649354 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.1591. Min Act: -0.1700
Data Index: 4242178 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5966. Min Range: -5.5966
Max Act: 5.1279. Min Act: -0.1700
Data Index: 7800688 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19