Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.2401. Min Act: -0.1700
Data Index: 7787435 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.2401. Min Act: -0.1700
Data Index: 6604946 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.2401. Min Act: -0.1700
Data Index: 3392644 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.2088. Min Act: -0.1700
Data Index: 7548490 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.2088. Min Act: -0.1700
Data Index: 2434264 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.2088. Min Act: -0.1700
Data Index: 2742951 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.2088. Min Act: -0.1700
Data Index: 6548009 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1776. Min Act: -0.1700
Data Index: 6256859 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1776. Min Act: -0.1700
Data Index: 2066822 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1776. Min Act: -0.1700
Data Index: 2026572 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 1396601 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 965558 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 6548010 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 3505665 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 6341064 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 3116298 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 5862086 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 4467183 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 1409428 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 4443280 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19