Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.3526. Min Act: -0.1700
Data Index: 8019356 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.3526. Min Act: -0.1700
Data Index: 6554892 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.2900. Min Act: -0.1700
Data Index: 3788032 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.2588. Min Act: -0.1700
Data Index: 2982713 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.2275. Min Act: -0.1700
Data Index: 7518411 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1963. Min Act: -0.1700
Data Index: 8667596 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1650. Min Act: -0.1700
Data Index: 458651 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1650. Min Act: -0.1700
Data Index: 7221158 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1025. Min Act: -0.1700
Data Index: 3076228 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1338. Min Act: -0.1700
Data Index: 6666948 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1338. Min Act: -0.1700
Data Index: 1184634 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1338. Min Act: -0.1700
Data Index: 1960817 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1025. Min Act: -0.1700
Data Index: 6591394 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1025. Min Act: -0.1700
Data Index: 903817 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1025. Min Act: -0.1700
Data Index: 6267310 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.0400. Min Act: -0.1700
Data Index: 360794 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.0713. Min Act: -0.1700
Data Index: 3543713 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1025. Min Act: -0.1700
Data Index: 2886989 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.0400. Min Act: -0.1700
Data Index: 5092921 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3526. Min Range: -4.3526
Max Act: 4.1025. Min Act: -0.1700
Data Index: 3002814 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19