Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.9079. Min Act: -0.1700
Data Index: 1093051 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.3766. Min Act: -0.1700
Data Index: 6806686 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.2516. Min Act: -0.1700
Data Index: 451325 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.2516. Min Act: -0.1700
Data Index: 3661367 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.2516. Min Act: -0.1700
Data Index: 7980201 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.1579. Min Act: -0.1700
Data Index: 262375 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.0954. Min Act: -0.1700
Data Index: 3858624 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.0329. Min Act: -0.1700
Data Index: 5471405 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.0016. Min Act: -0.1700
Data Index: 7928885 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9079. Min Range: -7.9079
Max Act: 7.0016. Min Act: -0.1700
Data Index: 7310785 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.9079. Min Act: -0.1700
Data Index: 5290995 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.8766. Min Act: -0.1700
Data Index: 5123095 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.9079. Min Act: -0.1700
Data Index: 2447892 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.8766. Min Act: -0.1700
Data Index: 2196281 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.9079. Min Act: -0.1700
Data Index: 8435077 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.8454. Min Act: -0.1700
Data Index: 1703897 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.8454. Min Act: -0.1700
Data Index: 7489851 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.8454. Min Act: -0.1700
Data Index: 428419 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.8454. Min Act: -0.1700
Data Index: 415145 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9079. Min Range: -7.9079
Max Act: 6.8141. Min Act: -0.1700
Data Index: 5360742 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19