Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.6819. Min Act: -0.1700
Data Index: 5364601 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.6384. Min Act: -0.1671
Data Index: 5985754 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.6297. Min Act: -0.1700
Data Index: 7391113 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.6035. Min Act: -0.1700
Data Index: 1178144 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.6035. Min Act: -0.1695
Data Index: 4415008 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5861. Min Act: -0.1700
Data Index: 3542472 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5686. Min Act: -0.1685
Data Index: 5485437 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5773. Min Act: -0.1700
Data Index: 696115 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5686. Min Act: -0.1586
Data Index: 2682070 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5686. Min Act: -0.1700
Data Index: 4373075 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5686. Min Act: -0.1698
Data Index: 4488160 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5598. Min Act: -0.1699
Data Index: 4860789 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5686. Min Act: -0.1694
Data Index: 5669415 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5598. Min Act: -0.1700
Data Index: 4837465 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5598. Min Act: -0.1594
Data Index: 3624711 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5598. Min Act: -0.1700
Data Index: 3070381 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5423. Min Act: -0.1655
Data Index: 7634493 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5511. Min Act: -0.1700
Data Index: 1473923 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5423. Min Act: -0.1698
Data Index: 4488165 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6819. Min Range: -1.6819
Max Act: 1.5511. Min Act: -0.1700
Data Index: 6134341 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19