Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.2417. Min Act: -0.1700
Data Index: 5608560 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.2417. Min Act: -0.1700
Data Index: 4710595 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.1792. Min Act: -0.1700
Data Index: 2711478 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.1167. Min Act: -0.1700
Data Index: 5873599 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0542. Min Act: -0.1699
Data Index: 6420051 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0542. Min Act: -0.1700
Data Index: 6483371 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0542. Min Act: -0.1697
Data Index: 1920826 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0542. Min Act: -0.1700
Data Index: 3740993 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0230. Min Act: -0.1700
Data Index: 8814651 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0542. Min Act: -0.1700
Data Index: 1206964 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0855. Min Act: -0.1700
Data Index: 6341065 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0542. Min Act: -0.1700
Data Index: 2601093 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0230. Min Act: -0.1700
Data Index: 2109279 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0542. Min Act: -0.1699
Data Index: 2601090 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0230. Min Act: -0.1700
Data Index: 6028136 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2417. Min Range: -5.2417
Max Act: 4.9917. Min Act: -0.1700
Data Index: 6025010 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0230. Min Act: -0.1700
Data Index: 3290421 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2417. Min Range: -5.2417
Max Act: 5.0230. Min Act: -0.1700
Data Index: 183305 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2417. Min Range: -5.2417
Max Act: 4.9917. Min Act: -0.1700
Data Index: 986888 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2417. Min Range: -5.2417
Max Act: 4.9917. Min Act: -0.1698
Data Index: 6432265 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19