Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.7412. Min Act: -0.1700
Data Index: 2490709 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.7412. Min Act: -0.1700
Data Index: 6107134 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.7412. Min Act: -0.1700
Data Index: 7722345 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.6787. Min Act: -0.1700
Data Index: 5265478 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.6162. Min Act: -0.1700
Data Index: 409800 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.5537. Min Act: -0.1700
Data Index: 418612 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.5537. Min Act: -0.1700
Data Index: 4713709 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.5537. Min Act: -0.1700
Data Index: 418613 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.5537. Min Act: -0.1700
Data Index: 1391800 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.4287. Min Act: -0.1700
Data Index: 5672532 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.4287. Min Act: -0.1700
Data Index: 3901007 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3662. Min Act: -0.1700
Data Index: 4690905 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3662. Min Act: -0.1700
Data Index: 4313546 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3662. Min Act: -0.1700
Data Index: 5961888 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3662. Min Act: -0.1700
Data Index: 8439452 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3662. Min Act: -0.1700
Data Index: 5110116 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3037. Min Act: -0.1700
Data Index: 1393615 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3037. Min Act: -0.1700
Data Index: 3739907 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3037. Min Act: -0.1700
Data Index: 244296 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7412. Min Range: -9.7412
Max Act: 9.3037. Min Act: -0.1700
Data Index: 1664778 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19