Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5605 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1800. Min Range: -5.1800
Max Act: 5.1800. Min Act: -0.1700
Data Index: 6653154 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1800. Min Range: -5.1800
Max Act: 5.1487. Min Act: -0.1700
Data Index: 786107 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1800. Min Range: -5.1800
Max Act: 5.0550. Min Act: -0.1700
Data Index: 4051021 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1800. Min Range: -5.1800
Max Act: 5.0862. Min Act: -0.1700
Data Index: 1208285 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1800. Min Range: -5.1800
Max Act: 5.0237. Min Act: -0.1700
Data Index: 7356332 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1800. Min Range: -5.1800
Max Act: 5.0237. Min Act: -0.1700
Data Index: 4857668 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.9925. Min Act: -0.1700
Data Index: 6385156 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.9925. Min Act: -0.1700
Data Index: 1709604 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.9612. Min Act: -0.1700
Data Index: 2843782 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8987. Min Act: -0.1700
Data Index: 3821930 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8675. Min Act: -0.1700
Data Index: 1166134 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8362. Min Act: -0.1700
Data Index: 5061670 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8675. Min Act: -0.1700
Data Index: 4706480 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8362. Min Act: -0.1700
Data Index: 7324191 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8362. Min Act: -0.1700
Data Index: 3519327 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8362. Min Act: -0.1700
Data Index: 5915667 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8050. Min Act: -0.1700
Data Index: 7642045 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8362. Min Act: -0.1700
Data Index: 2778200 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8050. Min Act: -0.1700
Data Index: 1309443 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1800. Min Range: -5.1800
Max Act: 4.8050. Min Act: -0.1700
Data Index: 3004936 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19