Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1503. Min Range: -6.1503
Max Act: 6.1503. Min Act: -0.1700
Data Index: 1394538 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1503. Min Range: -6.1503
Max Act: 6.0565. Min Act: -0.1700
Data Index: 7356281 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.9940. Min Act: -0.1700
Data Index: 4013436 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.9628. Min Act: -0.1700
Data Index: 7427566 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.9940. Min Act: -0.1700
Data Index: 6298366 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.9315. Min Act: -0.1700
Data Index: 722258 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.9003. Min Act: -0.1700
Data Index: 1255562 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.8690. Min Act: -0.1700
Data Index: 8416759 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.9003. Min Act: -0.1700
Data Index: 2217628 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.8378. Min Act: -0.1700
Data Index: 8462510 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.8065. Min Act: -0.1700
Data Index: 6212382 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.8065. Min Act: -0.1700
Data Index: 4492568 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.8065. Min Act: -0.1700
Data Index: 6915903 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.8065. Min Act: -0.1700
Data Index: 7511858 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.7753. Min Act: -0.1700
Data Index: 1906444 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.7753. Min Act: -0.1700
Data Index: 302568 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.7753. Min Act: -0.1700
Data Index: 1183397 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.7440. Min Act: -0.1700
Data Index: 3352106 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.7128. Min Act: -0.1700
Data Index: 7162162 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1503. Min Range: -6.1503
Max Act: 5.6815. Min Act: -0.1700
Data Index: 5427411 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19