Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8395. Min Range: -8.8395
Max Act: 8.8395. Min Act: -0.1700
Data Index: 7250483 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8395. Min Range: -8.8395
Max Act: 8.0895. Min Act: -0.1700
Data Index: 847554 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8395. Min Range: -8.8395
Max Act: 8.0270. Min Act: -0.1700
Data Index: 3471724 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.9645. Min Act: -0.1700
Data Index: 3750653 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.9020. Min Act: -0.1700
Data Index: 2858196 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.8395. Min Act: -0.1700
Data Index: 2542458 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.8395. Min Act: -0.1700
Data Index: 6699949 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.8395. Min Act: -0.1700
Data Index: 8042386 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.7145. Min Act: -0.1700
Data Index: 8603355 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.6833. Min Act: -0.1700
Data Index: 6146929 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.7145. Min Act: -0.1700
Data Index: 2781768 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.7145. Min Act: -0.1700
Data Index: 552906 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.6833. Min Act: -0.1700
Data Index: 7265307 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.6520. Min Act: -0.1700
Data Index: 4623230 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.6520. Min Act: -0.1700
Data Index: 5095006 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.5583. Min Act: -0.1700
Data Index: 921722 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.5270. Min Act: -0.1700
Data Index: 4510534 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.5270. Min Act: -0.1700
Data Index: 6516607 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.5270. Min Act: -0.1700
Data Index: 8349876 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8395. Min Range: -8.8395
Max Act: 7.4958. Min Act: -0.1700
Data Index: 4769891 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19