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

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

Neuron 48 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6900. Min Range: -4.6900

Max Act: 4.6900. Min Act: -0.0000

Data Index: 618368 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 4.6900. Min Range: -4.6900

Max Act: 4.0131. Min Act: -0.0000

Data Index: 1098936 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.6504. Min Act: -0.0000

Data Index: 1173933 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.7897. Min Act: -0.0000

Data Index: 51929 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.6664. Min Act: -0.0000

Data Index: 1004642 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.4372. Min Act: -0.0000

Data Index: 573516 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.7088. Min Act: -0.0000

Data Index: 1350339 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.5491. Min Act: -0.0000

Data Index: 588689 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.6946. Min Act: -0.0000

Data Index: 1120473 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.8377. Min Act: -0.0000

Data Index: 625278 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.6517. Min Act: -0.0000

Data Index: 1236970 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.6675. Min Act: -0.0000

Data Index: 1020094 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.6546. Min Act: -0.0000

Data Index: 1066427 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.5504. Min Act: -0.0000

Data Index: 355381 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.7356. Min Act: -0.0000

Data Index: 341177 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.5405. Min Act: -0.0000

Data Index: 1167792 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.3613. Min Act: -0.0000

Data Index: 1002367 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.4957. Min Act: -0.0000

Data Index: 1146555 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.6768. Min Act: -0.0000

Data Index: 81444 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 4.6900. Min Range: -4.6900

Max Act: 3.2748. Min Act: -0.0000

Data Index: 911163 (C4 (Web Text))

Max Activating Token Index: 281