Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3463. Min Range: -6.3463
Max Act: 6.3463. Min Act: -0.1700
Data Index: 7660867 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.8463. Min Act: -0.1700
Data Index: 7468939 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.8463. Min Act: -0.1700
Data Index: 4592246 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.8151. Min Act: -0.1700
Data Index: 6555774 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.8151. Min Act: -0.1700
Data Index: 2543269 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.7838. Min Act: -0.1700
Data Index: 6337740 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.7213. Min Act: -0.1700
Data Index: 8787255 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.7213. Min Act: -0.1700
Data Index: 770199 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.7213. Min Act: -0.1700
Data Index: 3885418 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.6588. Min Act: -0.1700
Data Index: 148018 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.6588. Min Act: -0.1700
Data Index: 4296307 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.6276. Min Act: -0.1700
Data Index: 4468142 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.6276. Min Act: -0.1700
Data Index: 2635596 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.6276. Min Act: -0.1700
Data Index: 1753173 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.5963. Min Act: -0.1700
Data Index: 607274 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.5651. Min Act: -0.1700
Data Index: 6241952 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.5026. Min Act: -0.1700
Data Index: 5959623 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.5651. Min Act: -0.1700
Data Index: 3525044 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.4713. Min Act: -0.1700
Data Index: 3381441 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3463. Min Range: -6.3463
Max Act: 5.5338. Min Act: -0.1700
Data Index: 2045864 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19