Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6012 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0135. Min Range: -7.0135
Max Act: 7.0135. Min Act: -0.1700
Data Index: 2974978 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.9510. Min Act: -0.1700
Data Index: 5973488 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.8260. Min Act: -0.1700
Data Index: 739876 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.6698. Min Act: -0.1700
Data Index: 1201458 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.6073. Min Act: -0.1700
Data Index: 7693452 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.5448. Min Act: -0.1700
Data Index: 8373381 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.4510. Min Act: -0.1700
Data Index: 7566764 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.4823. Min Act: -0.1700
Data Index: 45747 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.4510. Min Act: -0.1700
Data Index: 31916 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.4510. Min Act: -0.1700
Data Index: 5016853 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.4198. Min Act: -0.1700
Data Index: 3412793 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.4510. Min Act: -0.1700
Data Index: 3669288 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.3885. Min Act: -0.1700
Data Index: 4514238 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.3573. Min Act: -0.1700
Data Index: 6743405 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.2948. Min Act: -0.1700
Data Index: 8218055 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.2635. Min Act: -0.1700
Data Index: 553299 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.2323. Min Act: -0.1700
Data Index: 4364899 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.2323. Min Act: -0.1700
Data Index: 4708372 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.2323. Min Act: -0.1700
Data Index: 1074048 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0135. Min Range: -7.0135
Max Act: 6.2635. Min Act: -0.1700
Data Index: 2210285 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19