Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5791 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.6959. Min Act: -0.1700
Data Index: 1231538 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.6647. Min Act: -0.1700
Data Index: 1398808 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.6647. Min Act: -0.1700
Data Index: 8305344 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.6022. Min Act: -0.1700
Data Index: 3108254 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.6022. Min Act: -0.1700
Data Index: 4136313 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5709. Min Act: -0.1700
Data Index: 4458049 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5579854 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5709. Min Act: -0.1700
Data Index: 1679055 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5709. Min Act: -0.1700
Data Index: 428416 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5709. Min Act: -0.1700
Data Index: 2565420 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5478157 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.6022. Min Act: -0.1700
Data Index: 1006246 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5397. Min Act: -0.1700
Data Index: 7579600 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5397. Min Act: -0.1700
Data Index: 8496108 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5709. Min Act: -0.1700
Data Index: 4723789 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5397. Min Act: -0.1700
Data Index: 4531471 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5397. Min Act: -0.1700
Data Index: 3215563 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5397. Min Act: -0.1700
Data Index: 6812356 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5084. Min Act: -0.1700
Data Index: 4530489 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6959. Min Range: -5.6959
Max Act: 5.5084. Min Act: -0.1700
Data Index: 4921856 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19