Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4202 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.8347. Min Act: -0.1700
Data Index: 1446861 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.7409. Min Act: -0.1700
Data Index: 3003942 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.6784. Min Act: -0.1700
Data Index: 5289267 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.6472. Min Act: -0.1700
Data Index: 109431 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5222. Min Act: -0.1700
Data Index: 8460696 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.4597. Min Act: -0.1700
Data Index: 422639 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.4597. Min Act: -0.1700
Data Index: 8801497 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3972. Min Act: -0.1700
Data Index: 278721 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3659. Min Act: -0.1700
Data Index: 7142374 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3347. Min Act: -0.1700
Data Index: 3238032 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3347. Min Act: -0.1700
Data Index: 526072 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3347. Min Act: -0.1700
Data Index: 3972365 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3347. Min Act: -0.1700
Data Index: 4283134 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3034. Min Act: -0.1700
Data Index: 6643552 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3034. Min Act: -0.1700
Data Index: 2847732 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3034. Min Act: -0.1700
Data Index: 1959016 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.3034. Min Act: -0.1700
Data Index: 2186235 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.2722. Min Act: -0.1700
Data Index: 665404 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.2722. Min Act: -0.1700
Data Index: 8038497 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.2722. Min Act: -0.1700
Data Index: 8496145 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19