Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.5446. Min Act: -0.1700
Data Index: 5633671 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.4196. Min Act: -0.1700
Data Index: 6379596 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.3884. Min Act: -0.1700
Data Index: 4010292 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.1696. Min Act: -0.1700
Data Index: 4275209 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.1696. Min Act: -0.1700
Data Index: 79104 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.1384. Min Act: -0.1700
Data Index: 2305295 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.1071. Min Act: -0.1700
Data Index: 4453395 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.0759. Min Act: -0.1700
Data Index: 4118677 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.0446. Min Act: -0.1700
Data Index: 3429459 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.0134. Min Act: -0.1700
Data Index: 1793825 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.0134. Min Act: -0.1700
Data Index: 7062415 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5446. Min Range: -6.5446
Max Act: 6.0134. Min Act: -0.1700
Data Index: 3656844 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5446. Min Range: -6.5446
Max Act: 5.9821. Min Act: -0.1700
Data Index: 564954 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5446. Min Range: -6.5446
Max Act: 5.9509. Min Act: -0.1700
Data Index: 5923169 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5446. Min Range: -6.5446
Max Act: 5.8884. Min Act: -0.1700
Data Index: 3421245 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5446. Min Range: -6.5446
Max Act: 5.9196. Min Act: -0.1700
Data Index: 1832742 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5446. Min Range: -6.5446
Max Act: 5.9196. Min Act: -0.1700
Data Index: 6370817 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5446. Min Range: -6.5446
Max Act: 5.9196. Min Act: -0.1700
Data Index: 1674660 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5446. Min Range: -6.5446
Max Act: 5.8884. Min Act: -0.1700
Data Index: 5754860 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5446. Min Range: -6.5446
Max Act: 5.8571. Min Act: -0.1700
Data Index: 5803327 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19