Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4244 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.4047. Min Act: -0.1700
Data Index: 8603725 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.3109. Min Act: -0.1700
Data Index: 4309783 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.2797. Min Act: -0.1700
Data Index: 5022348 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.1547. Min Act: -0.1700
Data Index: 7547529 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.1547. Min Act: -0.1700
Data Index: 3822215 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.1547. Min Act: -0.1700
Data Index: 1589691 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.1234. Min Act: -0.1700
Data Index: 1624370 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.1234. Min Act: -0.1700
Data Index: 1616696 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4047. Min Range: -5.4047
Max Act: 5.0297. Min Act: -0.1700
Data Index: 4552209 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9984. Min Act: -0.1700
Data Index: 6745931 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9672. Min Act: -0.1700
Data Index: 7512700 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9984. Min Act: -0.1700
Data Index: 4657312 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5047276 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9672. Min Act: -0.1700
Data Index: 4693432 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9984. Min Act: -0.1700
Data Index: 7029328 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9359. Min Act: -0.1700
Data Index: 5302702 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9672. Min Act: -0.1700
Data Index: 7276679 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9359. Min Act: -0.1700
Data Index: 8660393 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9359. Min Act: -0.1700
Data Index: 4186201 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4047. Min Range: -5.4047
Max Act: 4.9047. Min Act: -0.1700
Data Index: 1879946 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19