Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2360 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4593. Min Range: -8.4593
Max Act: 8.4593. Min Act: -0.1700
Data Index: 7075846 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.8968. Min Act: -0.1700
Data Index: 1041838 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.8968. Min Act: -0.1700
Data Index: 7122237 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.7718. Min Act: -0.1700
Data Index: 4615717 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.7718. Min Act: -0.1700
Data Index: 5975242 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.7718. Min Act: -0.1700
Data Index: 3786383 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.6468. Min Act: -0.1700
Data Index: 3558008 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.6468. Min Act: -0.1700
Data Index: 6554786 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.5843. Min Act: -0.1700
Data Index: 8474804 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.5843. Min Act: -0.1700
Data Index: 6399905 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.5843. Min Act: -0.1700
Data Index: 6179575 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.5218. Min Act: -0.1700
Data Index: 6967613 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.5530. Min Act: -0.1700
Data Index: 680145 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.5218. Min Act: -0.1700
Data Index: 82466 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.4593. Min Act: -0.1700
Data Index: 4882429 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.4905. Min Act: -0.1700
Data Index: 2843332 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.4593. Min Act: -0.1700
Data Index: 118139 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.4905. Min Act: -0.1700
Data Index: 5621215 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.4280. Min Act: -0.1700
Data Index: 3718027 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4593. Min Range: -8.4593
Max Act: 7.4593. Min Act: -0.1700
Data Index: 3075093 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19