Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1916 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.6678. Min Act: -0.1700
Data Index: 860106 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.6365. Min Act: -0.1700
Data Index: 3292826 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.4803. Min Act: -0.1700
Data Index: 860105 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.4178. Min Act: -0.1700
Data Index: 2132645 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.3865. Min Act: -0.1700
Data Index: 1702199 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.3553. Min Act: -0.1700
Data Index: 3987168 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.3240. Min Act: -0.1700
Data Index: 3292825 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.2615. Min Act: -0.1700
Data Index: 1858078 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.1990. Min Act: -0.1700
Data Index: 3807485 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.1365. Min Act: -0.1700
Data Index: 3292823 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.1053. Min Act: -0.1700
Data Index: 3953568 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.0740. Min Act: -0.1700
Data Index: 8178197 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.0740. Min Act: -0.1700
Data Index: 5127424 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.0115. Min Act: -0.1700
Data Index: 6078169 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6678. Min Range: -6.6678
Max Act: 5.9803. Min Act: -0.1700
Data Index: 3447282 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.0115. Min Act: -0.1700
Data Index: 3783290 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.0115. Min Act: -0.1700
Data Index: 4920835 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.0115. Min Act: -0.1700
Data Index: 3862955 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.0115. Min Act: -0.1700
Data Index: 3953566 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6678. Min Range: -6.6678
Max Act: 6.0115. Min Act: -0.1700
Data Index: 4155646 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19