Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3455. Min Range: -7.3455
Max Act: 7.3455. Min Act: -0.1700
Data Index: 3195464 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3455. Min Range: -7.3455
Max Act: 7.1580. Min Act: -0.1700
Data Index: 2149447 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3455. Min Range: -7.3455
Max Act: 7.1893. Min Act: -0.1700
Data Index: 8236161 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3455. Min Range: -7.3455
Max Act: 7.1268. Min Act: -0.1700
Data Index: 5321505 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3455. Min Range: -7.3455
Max Act: 7.0018. Min Act: -0.1700
Data Index: 4874611 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.9705. Min Act: -0.1700
Data Index: 609926 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.9080. Min Act: -0.1699
Data Index: 2149449 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.9393. Min Act: -0.1700
Data Index: 6769590 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.9080. Min Act: -0.1700
Data Index: 707942 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.8768. Min Act: -0.1700
Data Index: 2149444 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.8143. Min Act: -0.1700
Data Index: 7612175 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.8143. Min Act: -0.1700
Data Index: 5098450 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.8143. Min Act: -0.1700
Data Index: 6931225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.7205. Min Act: -0.1700
Data Index: 2149443 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.7830. Min Act: -0.1700
Data Index: 875528 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.7205. Min Act: -0.1700
Data Index: 2949714 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.7205. Min Act: -0.1700
Data Index: 4874615 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.7205. Min Act: -0.1700
Data Index: 5437245 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.7205. Min Act: -0.1700
Data Index: 6085277 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3455. Min Range: -7.3455
Max Act: 6.6893. Min Act: -0.1700
Data Index: 707943 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19