Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3012 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.4000. Min Act: -0.0001

Data Index: 286017 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.4084. Min Act: -0.0001

Data Index: 394119 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.4176. Min Act: -0.0001

Data Index: 79198 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.4110. Min Act: -0.0001

Data Index: 866330 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3753. Min Act: -0.0001

Data Index: 243096 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3706. Min Act: -0.0001

Data Index: 1274625 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3713. Min Act: -0.0001

Data Index: 1025749 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3551. Min Act: -0.0001

Data Index: 276256 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3775. Min Act: -0.0001

Data Index: 273145 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3623. Min Act: -0.0001

Data Index: 985013 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3571. Min Act: -0.0001

Data Index: 393323 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3526. Min Act: -0.0001

Data Index: 794483 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3553. Min Act: -0.0001

Data Index: 758636 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3433. Min Act: -0.0001

Data Index: 610628 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3499. Min Act: -0.0001

Data Index: 553071 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3494. Min Act: -0.0001

Data Index: 717845 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3324. Min Act: -0.0001

Data Index: 1180324 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3437. Min Act: -0.0001

Data Index: 748727 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3671. Min Act: -0.0001

Data Index: 412825 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3298. Min Act: -0.0001

Data Index: 429677 (C4 (Web Text))

Max Activating Token Index: 407