Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.4148. Min Act: -0.1700
Data Index: 4717198 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3678. Min Act: -0.1700
Data Index: 553993 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3678. Min Act: -0.1700
Data Index: 553978 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3521. Min Act: -0.1700
Data Index: 554006 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3521. Min Act: -0.1700
Data Index: 6129750 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3364. Min Act: -0.1700
Data Index: 553977 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3364. Min Act: -0.1700
Data Index: 553979 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3207. Min Act: -0.1700
Data Index: 344813 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3207. Min Act: -0.1700
Data Index: 554005 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3207. Min Act: -0.1700
Data Index: 8551180 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3050. Min Act: -0.1700
Data Index: 344808 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.3050. Min Act: -0.1700
Data Index: 554007 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2893. Min Act: -0.1700
Data Index: 553999 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2893. Min Act: -0.1700
Data Index: 553975 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2893. Min Act: -0.1700
Data Index: 3728309 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2736. Min Act: -0.1700
Data Index: 344812 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2579. Min Act: -0.1700
Data Index: 554008 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2579. Min Act: -0.1700
Data Index: 122689 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2422. Min Act: -0.1700
Data Index: 7615487 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4148. Min Range: -3.4148
Max Act: 3.2422. Min Act: -0.1700
Data Index: 553965 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19