Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5453. Min Range: -7.5453
Max Act: 7.5453. Min Act: -0.1700
Data Index: 2941123 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5453. Min Range: -7.5453
Max Act: 7.1703. Min Act: -0.1700
Data Index: 6349661 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5453. Min Range: -7.5453
Max Act: 7.1078. Min Act: -0.1700
Data Index: 7254995 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5453. Min Range: -7.5453
Max Act: 7.1390. Min Act: -0.1700
Data Index: 230775 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5453. Min Range: -7.5453
Max Act: 7.0453. Min Act: -0.1700
Data Index: 888997 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5453. Min Range: -7.5453
Max Act: 7.0453. Min Act: -0.1700
Data Index: 4860461 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5453. Min Range: -7.5453
Max Act: 7.0140. Min Act: -0.1700
Data Index: 406594 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.9828. Min Act: -0.1700
Data Index: 6014941 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.9515. Min Act: -0.1700
Data Index: 4511524 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.9828. Min Act: -0.1700
Data Index: 2779738 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.9515. Min Act: -0.1700
Data Index: 7640014 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.9203. Min Act: -0.1700
Data Index: 1915581 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.9203. Min Act: -0.1700
Data Index: 8331621 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.8890. Min Act: -0.1700
Data Index: 7326317 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.8890. Min Act: -0.1700
Data Index: 2224434 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.8890. Min Act: -0.1700
Data Index: 7457287 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.8890. Min Act: -0.1700
Data Index: 8242849 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.8890. Min Act: -0.1700
Data Index: 2363436 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.8578. Min Act: -0.1700
Data Index: 237151 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5453. Min Range: -7.5453
Max Act: 6.9203. Min Act: -0.1700
Data Index: 6899540 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19