Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4364 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1375. Min Range: -7.1375
Max Act: 7.1375. Min Act: -0.1700
Data Index: 6685534 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1375. Min Range: -7.1375
Max Act: 7.1375. Min Act: -0.1700
Data Index: 1209176 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1375. Min Range: -7.1375
Max Act: 7.1062. Min Act: -0.1700
Data Index: 715824 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.9812. Min Act: -0.1700
Data Index: 4857130 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.9500. Min Act: -0.1700
Data Index: 5059447 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.9812. Min Act: -0.1700
Data Index: 7284151 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8875. Min Act: -0.1700
Data Index: 3817709 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8562. Min Act: -0.1700
Data Index: 6521067 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8875. Min Act: -0.1700
Data Index: 117262 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8875. Min Act: -0.1700
Data Index: 2839245 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8875. Min Act: -0.1700
Data Index: 946221 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8250. Min Act: -0.1700
Data Index: 8338477 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8562. Min Act: -0.1700
Data Index: 3842556 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8250. Min Act: -0.1700
Data Index: 6912554 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.8250. Min Act: -0.1700
Data Index: 5727712 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.7937. Min Act: -0.1700
Data Index: 6386445 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.7625. Min Act: -0.1700
Data Index: 2708916 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.7937. Min Act: -0.1700
Data Index: 3817711 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.7937. Min Act: -0.1700
Data Index: 1094802 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1375. Min Range: -7.1375
Max Act: 6.7000. Min Act: -0.1700
Data Index: 2962278 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19