Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.4421. Min Act: -0.1700
Data Index: 748298 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.4109. Min Act: -0.1700
Data Index: 717594 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.2546. Min Act: -0.1700
Data Index: 3390063 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.2546. Min Act: -0.1700
Data Index: 5019156 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.2234. Min Act: -0.1700
Data Index: 4192718 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1921. Min Act: -0.1700
Data Index: 2724419 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1921. Min Act: -0.1700
Data Index: 748303 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1921. Min Act: -0.1700
Data Index: 4582524 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1609. Min Act: -0.1700
Data Index: 2970505 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1609. Min Act: -0.1700
Data Index: 6147573 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1609. Min Act: -0.1700
Data Index: 3226866 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1609. Min Act: -0.1700
Data Index: 5380433 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1296. Min Act: -0.1700
Data Index: 7233099 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1296. Min Act: -0.1700
Data Index: 1283084 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1296. Min Act: -0.1700
Data Index: 3980154 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1296. Min Act: -0.1700
Data Index: 6166559 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1296. Min Act: -0.1700
Data Index: 1544696 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1296. Min Act: -0.1700
Data Index: 6118671 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1296. Min Act: -0.1700
Data Index: 6693782 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4421. Min Range: -5.4421
Max Act: 5.1609. Min Act: -0.1700
Data Index: 6812066 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19