Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3853 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2301. Min Range: -8.2301
Max Act: 8.2301. Min Act: -0.1700
Data Index: 5468927 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2301. Min Range: -8.2301
Max Act: 8.2301. Min Act: -0.1700
Data Index: 1471537 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2301. Min Range: -8.2301
Max Act: 8.0426. Min Act: -0.1700
Data Index: 7218497 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2301. Min Range: -8.2301
Max Act: 8.0426. Min Act: -0.1700
Data Index: 6807977 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2301. Min Range: -8.2301
Max Act: 8.0426. Min Act: -0.1700
Data Index: 6125774 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2301. Min Range: -8.2301
Max Act: 8.0426. Min Act: -0.1700
Data Index: 3315247 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.9801. Min Act: -0.1700
Data Index: 6559039 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.9801. Min Act: -0.1700
Data Index: 6180524 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.9176. Min Act: -0.1700
Data Index: 6866498 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.9801. Min Act: -0.1700
Data Index: 5159090 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.8551. Min Act: -0.1700
Data Index: 2298974 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.8551. Min Act: -0.1700
Data Index: 8800489 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.8551. Min Act: -0.1700
Data Index: 5349784 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.8551. Min Act: -0.1700
Data Index: 7339882 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.8551. Min Act: -0.1700
Data Index: 1694034 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.7926. Min Act: -0.1700
Data Index: 6051069 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.7926. Min Act: -0.1700
Data Index: 5788864 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.7926. Min Act: -0.1700
Data Index: 1665119 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.7926. Min Act: -0.1700
Data Index: 4920195 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2301. Min Range: -8.2301
Max Act: 7.7926. Min Act: -0.1700
Data Index: 3446130 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19