Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.2747. Min Act: -0.1700
Data Index: 1295204 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.2435. Min Act: -0.1700
Data Index: 1869504 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.2122. Min Act: -0.1700
Data Index: 4994600 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.2122. Min Act: -0.1700
Data Index: 1329528 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.2122. Min Act: -0.1700
Data Index: 463593 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1810. Min Act: -0.1697
Data Index: 4906658 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 1996854 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1497. Min Act: -0.1700
Data Index: 8202347 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1497. Min Act: -0.1700
Data Index: 281390 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1497. Min Act: -0.1700
Data Index: 1042469 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.0872. Min Act: -0.1700
Data Index: 5932469 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1185. Min Act: -0.1699
Data Index: 1509554 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.0872. Min Act: -0.1699
Data Index: 7075841 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 1719168 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 7877974 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 4125254 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 8227488 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 8395128 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.1185. Min Act: -0.1700
Data Index: 326268 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2747. Min Range: -5.2747
Max Act: 5.0872. Min Act: -0.1700
Data Index: 1926901 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19