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

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

Neuron 30 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.4271. Min Act: 0.0000

Data Index: 1317205 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.4082. Min Act: 0.0000

Data Index: 721453 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3971. Min Act: -0.0000

Data Index: 359100 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3973. Min Act: -0.0000

Data Index: 944061 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3778. Min Act: -0.0000

Data Index: 538558 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1039013 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3872. Min Act: -0.0000

Data Index: 791707 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3590. Min Act: 0.0004

Data Index: 1276798 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3676. Min Act: -0.0001

Data Index: 1234788 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3578. Min Act: 0.0000

Data Index: 336452 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3510. Min Act: -0.0001

Data Index: 225612 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3469. Min Act: -0.0001

Data Index: 862211 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3496. Min Act: -0.0000

Data Index: 801509 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3278. Min Act: -0.0001

Data Index: 642664 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3440. Min Act: -0.0001

Data Index: 278473 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1205670 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1073630 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3489. Min Act: -0.0000

Data Index: 607950 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3354. Min Act: -0.0000

Data Index: 878004 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.4271. Min Range: -0.4271

Max Act: 0.3272. Min Act: -0.0000

Data Index: 926491 (C4 (Web Text))

Max Activating Token Index: 782