Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 812 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.2681. Min Act: -0.1700
Data Index: 7942855 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.2368. Min Act: -0.1700
Data Index: 5154446 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.2368. Min Act: -0.1700
Data Index: 4492758 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.1118. Min Act: -0.1700
Data Index: 2844151 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.1118. Min Act: -0.1700
Data Index: 8505091 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.0181. Min Act: -0.1700
Data Index: 1040781 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.0181. Min Act: -0.1700
Data Index: 4531667 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.0181. Min Act: -0.1700
Data Index: 8701735 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2681. Min Range: -5.2681
Max Act: 5.0181. Min Act: -0.1700
Data Index: 3636657 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9868. Min Act: -0.1700
Data Index: 5455579 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9868. Min Act: -0.1700
Data Index: 5755012 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9868. Min Act: -0.1700
Data Index: 4182951 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9868. Min Act: -0.1700
Data Index: 2396261 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9868. Min Act: -0.1700
Data Index: 6147524 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9868. Min Act: -0.1700
Data Index: 4225125 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9556. Min Act: -0.1700
Data Index: 1127127 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9556. Min Act: -0.1700
Data Index: 4423130 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9556. Min Act: -0.1700
Data Index: 5535230 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9556. Min Act: -0.1700
Data Index: 709561 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2681. Min Range: -5.2681
Max Act: 4.9243. Min Act: -0.1700
Data Index: 5027414 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19