Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.4305. Min Act: -0.1700
Data Index: 8650377 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.3680. Min Act: -0.1700
Data Index: 7949966 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.3680. Min Act: -0.1700
Data Index: 7949965 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.2742. Min Act: -0.1700
Data Index: 2257619 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.2117. Min Act: -0.1700
Data Index: 7736190 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.2117. Min Act: -0.1700
Data Index: 1688952 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.2117. Min Act: -0.1700
Data Index: 5909132 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0554. Min Act: -0.1700
Data Index: 2982402 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0554. Min Act: -0.1700
Data Index: 6580227 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0554. Min Act: -0.1700
Data Index: 7999470 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0242. Min Act: -0.1700
Data Index: 2701816 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0242. Min Act: -0.1700
Data Index: 6206621 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0242. Min Act: -0.1700
Data Index: 5637450 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4305. Min Range: -4.4305
Max Act: 4.0554. Min Act: -0.1700
Data Index: 3130567 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4305. Min Range: -4.4305
Max Act: 3.9929. Min Act: -0.1700
Data Index: 737362 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4305. Min Range: -4.4305
Max Act: 3.9929. Min Act: -0.1700
Data Index: 4353113 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4305. Min Range: -4.4305
Max Act: 3.9617. Min Act: -0.1700
Data Index: 4701823 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4305. Min Range: -4.4305
Max Act: 3.9304. Min Act: -0.1700
Data Index: 4517189 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4305. Min Range: -4.4305
Max Act: 3.9304. Min Act: -0.1700
Data Index: 4949599 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4305. Min Range: -4.4305
Max Act: 3.9304. Min Act: -0.1700
Data Index: 5319643 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19