Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4106 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.7407. Min Act: -0.1700
Data Index: 7505583 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.6470. Min Act: -0.1700
Data Index: 7354668 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.6157. Min Act: -0.1700
Data Index: 649084 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.6157. Min Act: -0.1700
Data Index: 6508837 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.5532. Min Act: -0.1700
Data Index: 7992273 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.5532. Min Act: -0.1700
Data Index: 8184783 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.4907. Min Act: -0.1700
Data Index: 1461944 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.5220. Min Act: -0.1700
Data Index: 8106241 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.5532. Min Act: -0.1700
Data Index: 6812429 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.5220. Min Act: -0.1700
Data Index: 4830605 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.4595. Min Act: -0.1700
Data Index: 2338155 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.4595. Min Act: -0.1700
Data Index: 3429995 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.4595. Min Act: -0.1700
Data Index: 2184947 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.4282. Min Act: -0.1700
Data Index: 5019151 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.3970. Min Act: -0.1700
Data Index: 5240398 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.4282. Min Act: -0.1700
Data Index: 2830851 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.3970. Min Act: -0.1700
Data Index: 6250127 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.3657. Min Act: -0.1700
Data Index: 5513117 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.3657. Min Act: -0.1700
Data Index: 1485152 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.3657. Min Act: -0.1700
Data Index: 810605 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19