Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4816 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.6492. Min Act: -0.1700
Data Index: 4515609 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.6010. Min Act: -0.1700
Data Index: 2181930 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.5688. Min Act: -0.1696
Data Index: 412751 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.5527. Min Act: -0.1700
Data Index: 8135615 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.5365. Min Act: -0.1700
Data Index: 4236265 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.5365. Min Act: -0.1699
Data Index: 4143149 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.5203. Min Act: -0.1700
Data Index: 7676757 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.5203. Min Act: -0.1696
Data Index: 4143159 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.5041. Min Act: -0.1700
Data Index: 2187888 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4879. Min Act: -0.1700
Data Index: 4464752 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4879. Min Act: -0.1700
Data Index: 2590728 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4879. Min Act: -0.1700
Data Index: 344121 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4717. Min Act: -0.1699
Data Index: 6053437 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4717. Min Act: -0.1700
Data Index: 506849 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4555. Min Act: -0.1700
Data Index: 1548011 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4555. Min Act: -0.1700
Data Index: 3905385 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4392. Min Act: -0.1700
Data Index: 6490266 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4392. Min Act: -0.1700
Data Index: 882794 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4392. Min Act: -0.1700
Data Index: 5624797 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6492. Min Range: -2.6492
Max Act: 2.4229. Min Act: -0.1699
Data Index: 3848725 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19