Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4017 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1403. Min Range: -11.1403
Max Act: 11.1403. Min Act: -0.1700
Data Index: 6585174 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.9528. Min Act: -0.1700
Data Index: 4151955 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.7653. Min Act: -0.1700
Data Index: 4965808 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.7653. Min Act: -0.1700
Data Index: 3265929 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.7028. Min Act: -0.1700
Data Index: 6701087 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.6403. Min Act: -0.1700
Data Index: 2307563 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.7028. Min Act: -0.1700
Data Index: 966485 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.6403. Min Act: -0.1700
Data Index: 4250705 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5778. Min Act: -0.1700
Data Index: 8774167 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5153. Min Act: -0.1700
Data Index: 7094313 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5778. Min Act: -0.1700
Data Index: 570882 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5778. Min Act: -0.1700
Data Index: 3916319 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5153. Min Act: -0.1700
Data Index: 3909710 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.6403. Min Act: -0.1700
Data Index: 4706941 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5778. Min Act: -0.1700
Data Index: 737576 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5778. Min Act: -0.1700
Data Index: 7874256 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5153. Min Act: -0.1699
Data Index: 3379851 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5153. Min Act: -0.1700
Data Index: 3742265 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.4528. Min Act: -0.1700
Data Index: 1787531 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1403. Min Range: -11.1403
Max Act: 10.5153. Min Act: -0.1700
Data Index: 6221548 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19