Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1699 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0517. Min Range: -4.0517
Max Act: 4.0517. Min Act: -0.1700
Data Index: 4953816 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.9579. Min Act: -0.1700
Data Index: 336418 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.9266. Min Act: -0.1700
Data Index: 1891734 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 748016 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 7877092 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.9579. Min Act: -0.1700
Data Index: 116986 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.9266. Min Act: -0.1700
Data Index: 4936286 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.9266. Min Act: -0.1700
Data Index: 5330223 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 2546415 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 2926190 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 2718573 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 2684443 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 8259378 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 7577748 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.9266. Min Act: -0.1700
Data Index: 116988 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 756561 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 7444587 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 685287 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8953. Min Act: -0.1700
Data Index: 224918 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0517. Min Range: -4.0517
Max Act: 3.8641. Min Act: -0.1700
Data Index: 116989 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19