Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2409 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0106. Min Range: -9.0106
Max Act: 9.0106. Min Act: -0.1700
Data Index: 3619999 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.6981. Min Act: -0.1700
Data Index: 6246339 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.6356. Min Act: -0.1700
Data Index: 910544 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.5731. Min Act: -0.1700
Data Index: 8729557 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.5106. Min Act: -0.1700
Data Index: 5515677 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.5106. Min Act: -0.1700
Data Index: 376760 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.5106. Min Act: -0.1700
Data Index: 8578746 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.5106. Min Act: -0.1700
Data Index: 2723465 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.4481. Min Act: -0.1700
Data Index: 7094273 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.3856. Min Act: -0.1700
Data Index: 296737 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.4481. Min Act: -0.1700
Data Index: 5446041 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.4481. Min Act: -0.1700
Data Index: 5066456 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.4481. Min Act: -0.1700
Data Index: 1363300 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.4481. Min Act: -0.1700
Data Index: 8409068 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.3856. Min Act: -0.1700
Data Index: 8618449 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.4481. Min Act: -0.1700
Data Index: 647353 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.3856. Min Act: -0.1700
Data Index: 4898089 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.3856. Min Act: -0.1700
Data Index: 5923554 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.2606. Min Act: -0.1700
Data Index: 740735 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0106. Min Range: -9.0106
Max Act: 8.3231. Min Act: -0.1700
Data Index: 4113806 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19