Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.7295. Min Act: -0.0000

Data Index: 865430 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1151823 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.6299. Min Act: -0.0001

Data Index: 921459 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.6057. Min Act: -0.0000

Data Index: 919667 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5995. Min Act: -0.0001

Data Index: 1061535 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5895. Min Act: -0.0000

Data Index: 406850 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.6009. Min Act: -0.0001

Data Index: 490438 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5603. Min Act: -0.0000

Data Index: 932021 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5786. Min Act: -0.0001

Data Index: 299080 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5372. Min Act: -0.0001

Data Index: 263332 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5678. Min Act: -0.0000

Data Index: 822605 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5668. Min Act: -0.0001

Data Index: 212609 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5466. Min Act: -0.0001

Data Index: 1205571 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5753. Min Act: -0.0001

Data Index: 757292 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5547. Min Act: -0.0001

Data Index: 593804 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5539. Min Act: -0.0001

Data Index: 578951 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5471. Min Act: -0.0001

Data Index: 600776 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5455. Min Act: -0.0000

Data Index: 715209 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5447. Min Act: -0.0001

Data Index: 465889 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5584. Min Act: -0.0001

Data Index: 188037 (C4 (Web Text))

Max Activating Token Index: 247