Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1720 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.4386. Min Act: -0.1700
Data Index: 466542 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.4074. Min Act: -0.1700
Data Index: 4680019 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3449. Min Act: -0.1700
Data Index: 3036655 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.3449. Min Act: -0.1700
Data Index: 2365522 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.2824. Min Act: -0.1700
Data Index: 1104928 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.2511. Min Act: -0.1700
Data Index: 5824419 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.2511. Min Act: -0.1700
Data Index: 7964818 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.2198. Min Act: -0.1700
Data Index: 2275533 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.2198. Min Act: -0.1700
Data Index: 4655442 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1573. Min Act: -0.1700
Data Index: 2275531 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1573. Min Act: -0.1700
Data Index: 7598360 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1886. Min Act: -0.1700
Data Index: 4582530 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1886. Min Act: -0.1700
Data Index: 6032261 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1573. Min Act: -0.1700
Data Index: 6816313 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1573. Min Act: -0.1700
Data Index: 4236939 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1573. Min Act: -0.1700
Data Index: 3584172 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1573. Min Act: -0.1700
Data Index: 6816317 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1573. Min Act: -0.1700
Data Index: 3622973 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1573. Min Act: -0.1700
Data Index: 4758748 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4386. Min Range: -4.4386
Max Act: 4.1261. Min Act: -0.1700
Data Index: 3429854 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19