Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.1378. Min Act: -0.1700
Data Index: 6290989 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0753. Min Act: -0.1700
Data Index: 6508554 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0753. Min Act: -0.1700
Data Index: 6242671 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0753. Min Act: -0.1700
Data Index: 8086660 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0441. Min Act: -0.1700
Data Index: 7648180 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0753. Min Act: -0.1700
Data Index: 8172090 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0753. Min Act: -0.1700
Data Index: 7528192 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0128. Min Act: -0.1700
Data Index: 4019869 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0128. Min Act: -0.1700
Data Index: 1923574 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9815. Min Act: -0.1700
Data Index: 1165809 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9815. Min Act: -0.1700
Data Index: 3822856 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9815. Min Act: -0.1700
Data Index: 2445557 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9815. Min Act: -0.1700
Data Index: 5463393 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9815. Min Act: -0.1700
Data Index: 2571276 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1378. Min Range: -4.1378
Max Act: 4.0128. Min Act: -0.1700
Data Index: 3716782 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9503. Min Act: -0.1700
Data Index: 817995 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9503. Min Act: -0.1700
Data Index: 5889122 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9503. Min Act: -0.1700
Data Index: 2908150 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9503. Min Act: -0.1700
Data Index: 6202667 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1378. Min Range: -4.1378
Max Act: 3.9503. Min Act: -0.1700
Data Index: 1482593 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19