Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5361 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.7398. Min Act: -0.1700
Data Index: 1427987 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.5835. Min Act: -0.1700
Data Index: 1449652 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.5210. Min Act: -0.1700
Data Index: 6769245 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.4898. Min Act: -0.1700
Data Index: 4552064 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.4273. Min Act: -0.1700
Data Index: 7957619 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.3960. Min Act: -0.1700
Data Index: 3974603 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.3648. Min Act: -0.1700
Data Index: 75339 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.3648. Min Act: -0.1700
Data Index: 3733587 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.3335. Min Act: -0.1700
Data Index: 8746473 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.3023. Min Act: -0.1700
Data Index: 7765804 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.3023. Min Act: -0.1700
Data Index: 6380792 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.3023. Min Act: -0.1700
Data Index: 445089 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.2710. Min Act: -0.1700
Data Index: 5772880 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.2398. Min Act: -0.1700
Data Index: 3643477 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.2398. Min Act: -0.1700
Data Index: 3806829 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.2398. Min Act: -0.1700
Data Index: 7382452 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.2398. Min Act: -0.1700
Data Index: 3346882 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.2398. Min Act: -0.1700
Data Index: 7660736 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.1773. Min Act: -0.1700
Data Index: 1237758 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7398. Min Range: -5.7398
Max Act: 5.1773. Min Act: -0.1700
Data Index: 1663852 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19