Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 807 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.3374. Min Range: -6.3374

Max Act: 6.3374. Min Act: -0.0000

Data Index: 1325447 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 6.3374. Min Range: -6.3374

Max Act: 6.2358. Min Act: -0.0000

Data Index: 1125671 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.9907. Min Act: -0.0000

Data Index: 1081609 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 6.3374. Min Range: -6.3374

Max Act: 6.0074. Min Act: -0.0000

Data Index: 1146331 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.5798. Min Act: -0.0001

Data Index: 143055 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.5320. Min Act: -0.0000

Data Index: 679242 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.3835. Min Act: -0.0001

Data Index: 1064148 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.7318. Min Act: -0.0000

Data Index: 39644 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.3616. Min Act: -0.0000

Data Index: 587779 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.6228. Min Act: -0.0000

Data Index: 969830 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.3765. Min Act: -0.0000

Data Index: 416247 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.7483. Min Act: -0.0000

Data Index: 862733 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.7313. Min Act: -0.0000

Data Index: 1035630 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.8952. Min Act: -0.0000

Data Index: 990151 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.6980. Min Act: -0.0000

Data Index: 1165589 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.6432. Min Act: -0.0000

Data Index: 1039900 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 6.3374. Min Range: -6.3374

Max Act: 6.1751. Min Act: -0.0001

Data Index: 206776 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.6415. Min Act: -0.0001

Data Index: 175356 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.6377. Min Act: -0.0001

Data Index: 1162643 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 6.3374. Min Range: -6.3374

Max Act: 5.4417. Min Act: -0.0000

Data Index: 929043 (C4 (Web Text))

Max Activating Token Index: 71