Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0248. Min Range: -8.0248
Max Act: 8.0248. Min Act: -0.1700
Data Index: 7671598 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.7748. Min Act: -0.1700
Data Index: 1075876 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.7123. Min Act: -0.1700
Data Index: 5187461 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.6498. Min Act: -0.1700
Data Index: 154872 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.6186. Min Act: -0.1700
Data Index: 2742478 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.5248. Min Act: -0.1700
Data Index: 4907554 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.4936. Min Act: -0.1700
Data Index: 389098 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.4311. Min Act: -0.1700
Data Index: 7990910 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.4311. Min Act: -0.1700
Data Index: 4288850 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3998. Min Act: -0.1700
Data Index: 314685 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3998. Min Act: -0.1700
Data Index: 6599413 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3686. Min Act: -0.1700
Data Index: 2867241 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3686. Min Act: -0.1700
Data Index: 6230046 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3373. Min Act: -0.1700
Data Index: 7997746 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3686. Min Act: -0.1700
Data Index: 6326764 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3373. Min Act: -0.1700
Data Index: 6533199 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3061. Min Act: -0.1700
Data Index: 1693151 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3061. Min Act: -0.1700
Data Index: 2493015 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3061. Min Act: -0.1700
Data Index: 883883 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0248. Min Range: -8.0248
Max Act: 7.3061. Min Act: -0.1700
Data Index: 3837953 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19