Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.8396. Min Act: -0.1700
Data Index: 4973584 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.5271. Min Act: -0.1700
Data Index: 7191788 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.3396. Min Act: -0.1699
Data Index: 4501313 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.3396. Min Act: -0.1700
Data Index: 2285193 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.3396. Min Act: -0.1700
Data Index: 1643365 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.3396. Min Act: -0.1700
Data Index: 5891813 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.2771. Min Act: -0.1700
Data Index: 3241712 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.2146. Min Act: -0.1700
Data Index: 4316949 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.2146. Min Act: -0.1700
Data Index: 1088871 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 6833403 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 4061302 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 2583013 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 4649549 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 7277681 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.1521. Min Act: -0.1700
Data Index: 8066317 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0896. Min Act: -0.1700
Data Index: 2533624 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0896. Min Act: -0.1700
Data Index: 6330 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0271. Min Act: -0.1700
Data Index: 322857 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0271. Min Act: -0.1700
Data Index: 4969873 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8396. Min Range: -8.8396
Max Act: 8.0271. Min Act: -0.1700
Data Index: 675286 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19