Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.5021. Min Act: -0.1700
Data Index: 6640604 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.4396. Min Act: -0.1700
Data Index: 1191899 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.3771. Min Act: -0.1700
Data Index: 3798509 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.3146. Min Act: -0.1700
Data Index: 5554907 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.2833. Min Act: -0.1700
Data Index: 6028573 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.2833. Min Act: -0.1700
Data Index: 1693707 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.2521. Min Act: -0.1700
Data Index: 8060741 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.2208. Min Act: -0.1700
Data Index: 5172375 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.1896. Min Act: -0.1700
Data Index: 628212 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.1271. Min Act: -0.1700
Data Index: 8241631 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.0958. Min Act: -0.1700
Data Index: 8087592 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.0958. Min Act: -0.1700
Data Index: 8298777 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.0333. Min Act: -0.1700
Data Index: 8512773 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5021. Min Range: -5.5021
Max Act: 5.0021. Min Act: -0.1700
Data Index: 4532924 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5021. Min Range: -5.5021
Max Act: 4.9708. Min Act: -0.1700
Data Index: 3832352 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5021. Min Range: -5.5021
Max Act: 4.9708. Min Act: -0.1700
Data Index: 3574540 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5021. Min Range: -5.5021
Max Act: 4.9396. Min Act: -0.1700
Data Index: 630050 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5021. Min Range: -5.5021
Max Act: 4.9083. Min Act: -0.1700
Data Index: 7100958 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5021. Min Range: -5.5021
Max Act: 4.9396. Min Act: -0.1700
Data Index: 4035079 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5021. Min Range: -5.5021
Max Act: 4.9396. Min Act: -0.1700
Data Index: 2526965 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19