Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 678 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.5919. Min Act: -0.1700
Data Index: 2059411 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.5606. Min Act: -0.1700
Data Index: 5972859 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.5606. Min Act: -0.1700
Data Index: 6559025 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.5606. Min Act: -0.1700
Data Index: 3707369 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.5294. Min Act: -0.1700
Data Index: 7880928 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.2481. Min Act: -0.1700
Data Index: 841397 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.2481. Min Act: -0.1700
Data Index: 2374243 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.2481. Min Act: -0.1700
Data Index: 1227100 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.2169. Min Act: -0.1700
Data Index: 5408885 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.1544. Min Act: -0.1700
Data Index: 8110403 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.1856. Min Act: -0.1700
Data Index: 4501532 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.1544. Min Act: -0.1700
Data Index: 417226 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.1231. Min Act: -0.1700
Data Index: 764737 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.0606. Min Act: -0.1700
Data Index: 1206002 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.1231. Min Act: -0.1700
Data Index: 1075065 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.0606. Min Act: -0.1700
Data Index: 6861135 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.0294. Min Act: -0.1700
Data Index: 490627 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.0606. Min Act: -0.1700
Data Index: 2468997 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.0606. Min Act: -0.1700
Data Index: 5313993 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5919. Min Range: -5.5919
Max Act: 5.0606. Min Act: -0.1700
Data Index: 378066 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19