Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2772. Min Range: -7.2772
Max Act: 7.2772. Min Act: -0.1700
Data Index: 4254543 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.9959. Min Act: -0.1700
Data Index: 8244108 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.6834. Min Act: -0.1700
Data Index: 4254548 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.6834. Min Act: -0.1700
Data Index: 4254526 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.6834. Min Act: -0.1700
Data Index: 5047509 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.5897. Min Act: -0.1700
Data Index: 4254542 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.5584. Min Act: -0.1700
Data Index: 2820490 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.5584. Min Act: -0.1700
Data Index: 1327492 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.5584. Min Act: -0.1700
Data Index: 4830829 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.4959. Min Act: -0.1700
Data Index: 5537861 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.4959. Min Act: -0.1700
Data Index: 5204861 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.4647. Min Act: -0.1700
Data Index: 1579611 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.4334. Min Act: -0.1700
Data Index: 3038416 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.3709. Min Act: -0.1700
Data Index: 7141306 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.4022. Min Act: -0.1700
Data Index: 1955591 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.4022. Min Act: -0.1700
Data Index: 2853297 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.3709. Min Act: -0.1700
Data Index: 4359831 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.3397. Min Act: -0.1700
Data Index: 3370632 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.3709. Min Act: -0.1700
Data Index: 1117845 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2772. Min Range: -7.2772
Max Act: 6.3397. Min Act: -0.1700
Data Index: 2278180 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19