Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.6434. Min Act: -0.1700
Data Index: 3936325 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.3622. Min Act: -0.1699
Data Index: 7367357 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.3309. Min Act: -0.1700
Data Index: 510693 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.2372. Min Act: -0.1700
Data Index: 5977299 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.2372. Min Act: -0.1700
Data Index: 5104576 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.2059. Min Act: -0.1700
Data Index: 7650273 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.2059. Min Act: -0.1700
Data Index: 2997320 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.1747. Min Act: -0.1700
Data Index: 5567230 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.1747. Min Act: -0.1700
Data Index: 1677237 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.2059. Min Act: -0.1700
Data Index: 7367371 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.1434. Min Act: -0.1700
Data Index: 6056026 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.1747. Min Act: -0.1700
Data Index: 7283461 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.0809. Min Act: -0.1700
Data Index: 7713287 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.0809. Min Act: -0.1700
Data Index: 3091693 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.0809. Min Act: -0.1700
Data Index: 3130613 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6434. Min Range: -6.6434
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4258001 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.0497. Min Act: -0.1700
Data Index: 3689644 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.0809. Min Act: -0.1700
Data Index: 3618336 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6434. Min Range: -6.6434
Max Act: 6.0497. Min Act: -0.1700
Data Index: 1697514 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6434. Min Range: -6.6434
Max Act: 5.9872. Min Act: -0.1700
Data Index: 6610546 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19