Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 389 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.3210. Min Act: -0.1700
Data Index: 7407833 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.3045. Min Act: -0.1700
Data Index: 4961844 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2716. Min Act: -0.1700
Data Index: 5153799 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2386. Min Act: -0.1700
Data Index: 7868435 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2551. Min Act: -0.1700
Data Index: 2968329 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2551. Min Act: -0.1699
Data Index: 3343267 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2716. Min Act: -0.1700
Data Index: 1643252 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2551. Min Act: -0.1700
Data Index: 1631190 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2551. Min Act: -0.1700
Data Index: 1803887 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2386. Min Act: -0.1680
Data Index: 6758537 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2220. Min Act: -0.1700
Data Index: 5447477 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2220. Min Act: -0.1700
Data Index: 5572618 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.2055. Min Act: -0.1700
Data Index: 7094513 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.1889. Min Act: -0.1700
Data Index: 4207958 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.1889. Min Act: -0.1691
Data Index: 6864993 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.1722. Min Act: -0.1700
Data Index: 4700366 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.1889. Min Act: -0.1700
Data Index: 3975402 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.1556. Min Act: -0.1696
Data Index: 3642576 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.1722. Min Act: -0.1700
Data Index: 2062826 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3210. Min Range: -2.3210
Max Act: 2.1722. Min Act: -0.1700
Data Index: 2122999 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19