Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.5196. Min Act: -0.1700
Data Index: 3525004 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.5509. Min Act: -0.1700
Data Index: 6200916 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.4571. Min Act: -0.1700
Data Index: 6795942 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.3946. Min Act: -0.1700
Data Index: 3074101 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.3009. Min Act: -0.1700
Data Index: 6405140 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.3009. Min Act: -0.1700
Data Index: 6081850 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.3009. Min Act: -0.1700
Data Index: 4915531 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.2384. Min Act: -0.1700
Data Index: 1191392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.2696. Min Act: -0.1700
Data Index: 1436974 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.2696. Min Act: -0.1700
Data Index: 3243759 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.2384. Min Act: -0.1700
Data Index: 4388391 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.2384. Min Act: -0.1700
Data Index: 8212241 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.2384. Min Act: -0.1700
Data Index: 2775400 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.2071. Min Act: -0.1700
Data Index: 3074102 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.1759. Min Act: -0.1700
Data Index: 1820361 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.1759. Min Act: -0.1700
Data Index: 617849 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.1446. Min Act: -0.1700
Data Index: 6344963 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.1446. Min Act: -0.1700
Data Index: 3793207 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.1446. Min Act: -0.1700
Data Index: 148101 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5509. Min Range: -5.5509
Max Act: 5.1446. Min Act: -0.1700
Data Index: 3468610 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19