Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.6592. Min Act: -0.1700
Data Index: 4707686 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.6279. Min Act: -0.1700
Data Index: 6856308 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.6279. Min Act: -0.1700
Data Index: 4964787 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.6279. Min Act: -0.1700
Data Index: 2760708 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.5340. Min Act: -0.1700
Data Index: 5238390 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.4557. Min Act: -0.1700
Data Index: 2385084 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.4244. Min Act: -0.1700
Data Index: 8288581 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.3930. Min Act: -0.1700
Data Index: 244518 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.3773. Min Act: -0.1700
Data Index: 1597339 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.3460. Min Act: -0.1700
Data Index: 8825109 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.3616. Min Act: -0.1700
Data Index: 409157 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.3303. Min Act: -0.1700
Data Index: 4113867 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.3146. Min Act: -0.1700
Data Index: 5270682 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.3146. Min Act: -0.1700
Data Index: 3636243 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.3146. Min Act: -0.1700
Data Index: 6754323 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.2989. Min Act: -0.1700
Data Index: 6163538 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.2832. Min Act: -0.1700
Data Index: 4054426 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.2989. Min Act: -0.1700
Data Index: 7171688 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.2989. Min Act: -0.1700
Data Index: 2966428 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6592. Min Range: -3.6592
Max Act: 3.2989. Min Act: -0.1700
Data Index: 5291186 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19