Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5241 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.8323. Min Act: -0.1700
Data Index: 5549409 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.5510. Min Act: -0.1700
Data Index: 5292038 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.4573. Min Act: -0.1700
Data Index: 4709545 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.3948. Min Act: -0.1700
Data Index: 2720476 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.4260. Min Act: -0.1700
Data Index: 7805808 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.3948. Min Act: -0.1700
Data Index: 3802143 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.3948. Min Act: -0.1700
Data Index: 2091862 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.3635. Min Act: -0.1700
Data Index: 801132 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.3323. Min Act: -0.1700
Data Index: 6918727 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.3010. Min Act: -0.1700
Data Index: 3891603 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.3010. Min Act: -0.1700
Data Index: 7683056 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.2698. Min Act: -0.1700
Data Index: 6695490 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.2385. Min Act: -0.1700
Data Index: 7931234 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.2073. Min Act: -0.1700
Data Index: 1002753 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.2073. Min Act: -0.1700
Data Index: 4919860 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.1760. Min Act: -0.1700
Data Index: 3293169 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.1448. Min Act: -0.1700
Data Index: 4632908 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.1760. Min Act: -0.1700
Data Index: 7095058 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.1448. Min Act: -0.1700
Data Index: 2080619 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8323. Min Range: -6.8323
Max Act: 6.1448. Min Act: -0.1700
Data Index: 5083835 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19