Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1471. Min Range: -5.1471
Max Act: 5.1471. Min Act: -0.1700
Data Index: 62087 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1471. Min Range: -5.1471
Max Act: 5.1158. Min Act: -0.1700
Data Index: 693892 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1471. Min Range: -5.1471
Max Act: 5.0221. Min Act: -0.1700
Data Index: 6537980 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1471. Min Range: -5.1471
Max Act: 5.0221. Min Act: -0.1700
Data Index: 2884117 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1471. Min Range: -5.1471
Max Act: 5.0221. Min Act: -0.1700
Data Index: 3142662 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.8971. Min Act: -0.1700
Data Index: 6315100 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.9596. Min Act: -0.1700
Data Index: 2420201 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.8658. Min Act: -0.1700
Data Index: 8525960 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.9283. Min Act: -0.1700
Data Index: 5546250 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.8658. Min Act: -0.1700
Data Index: 4019305 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.8658. Min Act: -0.1700
Data Index: 1701041 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.8033. Min Act: -0.1700
Data Index: 1173413 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.8033. Min Act: -0.1700
Data Index: 2616992 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.7721. Min Act: -0.1700
Data Index: 1256882 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.7721. Min Act: -0.1700
Data Index: 7705068 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.7721. Min Act: -0.1700
Data Index: 7164036 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.7408. Min Act: -0.1700
Data Index: 3495728 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.7408. Min Act: -0.1700
Data Index: 2002619 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.7408. Min Act: -0.1700
Data Index: 8519262 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1471. Min Range: -5.1471
Max Act: 4.6783. Min Act: -0.1700
Data Index: 2789809 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19