Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 681 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.4750. Min Act: -0.1700
Data Index: 28707 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.4750. Min Act: -0.1700
Data Index: 5048093 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.4437. Min Act: -0.1700
Data Index: 5707625 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.4437. Min Act: -0.1700
Data Index: 6086912 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.3812. Min Act: -0.1700
Data Index: 5645649 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.3812. Min Act: -0.1700
Data Index: 4753616 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.3812. Min Act: -0.1700
Data Index: 2074436 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.3500. Min Act: -0.1700
Data Index: 2641362 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.3187. Min Act: -0.1700
Data Index: 1890231 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.2875. Min Act: -0.1700
Data Index: 1445156 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.2875. Min Act: -0.1700
Data Index: 2718143 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.2250. Min Act: -0.1700
Data Index: 5760668 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.2250. Min Act: -0.1700
Data Index: 5838982 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.2250. Min Act: -0.1700
Data Index: 5122539 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.1625. Min Act: -0.1700
Data Index: 4334499 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.1625. Min Act: -0.1700
Data Index: 4652445 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.1000. Min Act: -0.1700
Data Index: 6028286 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.1312. Min Act: -0.1700
Data Index: 595224 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.1000. Min Act: -0.1700
Data Index: 8581850 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4750. Min Range: -6.4750
Max Act: 6.0687. Min Act: -0.1700
Data Index: 8666877 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19