Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.4596. Min Act: -0.1700
Data Index: 4686313 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.4596. Min Act: -0.1700
Data Index: 1155648 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.3659. Min Act: -0.1700
Data Index: 2126351 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.3659. Min Act: -0.1700
Data Index: 4545879 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.3659. Min Act: -0.1700
Data Index: 6499222 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.3346. Min Act: -0.1700
Data Index: 8086586 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.3034. Min Act: -0.1700
Data Index: 6619596 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.3034. Min Act: -0.1700
Data Index: 909243 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2409. Min Act: -0.1700
Data Index: 4432508 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2096. Min Act: -0.1700
Data Index: 4679332 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2721. Min Act: -0.1700
Data Index: 293335 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2721. Min Act: -0.1700
Data Index: 7339082 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2409. Min Act: -0.1700
Data Index: 2510035 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2721. Min Act: -0.1700
Data Index: 1295769 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2721. Min Act: -0.1700
Data Index: 1291823 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2096. Min Act: -0.1700
Data Index: 5678393 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2096. Min Act: -0.1700
Data Index: 2020754 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2409. Min Act: -0.1700
Data Index: 1998160 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2096. Min Act: -0.1700
Data Index: 2222164 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4596. Min Range: -4.4596
Max Act: 4.2409. Min Act: -0.1700
Data Index: 2265087 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19