Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4045 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.5191. Min Act: -0.1700
Data Index: 512814 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.1109. Min Act: -0.1700
Data Index: 4986150 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0951. Min Act: -0.1700
Data Index: 4904755 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0951. Min Act: -0.1700
Data Index: 8667380 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.1109. Min Act: -0.1700
Data Index: 7763315 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0636. Min Act: -0.1700
Data Index: 7839348 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0478. Min Act: -0.1700
Data Index: 8079108 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0320. Min Act: -0.1700
Data Index: 7035130 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0320. Min Act: -0.1700
Data Index: 2435103 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0478. Min Act: -0.1700
Data Index: 5097644 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0004. Min Act: -0.1700
Data Index: 3802858 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0162. Min Act: -0.1700
Data Index: 1878721 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0162. Min Act: -0.1700
Data Index: 2319671 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0004. Min Act: -0.1700
Data Index: 4857598 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0004. Min Act: -0.1700
Data Index: 6298477 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5191. Min Range: -3.5191
Max Act: 2.9846. Min Act: -0.1700
Data Index: 4898538 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0004. Min Act: -0.1700
Data Index: 8125351 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5191. Min Range: -3.5191
Max Act: 3.0004. Min Act: -0.1700
Data Index: 5436144 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5191. Min Range: -3.5191
Max Act: 2.9530. Min Act: -0.1700
Data Index: 475398 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5191. Min Range: -3.5191
Max Act: 2.9530. Min Act: -0.1700
Data Index: 6697546 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19