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

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

Neuron 1063 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1005227 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.1498. Min Act: -0.0000

Data Index: 53548 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.1106. Min Act: -0.0000

Data Index: 862384 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.1323. Min Act: -0.0001

Data Index: 1173709 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.0547. Min Act: -0.0001

Data Index: 1260832 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.0176. Min Act: -0.0000

Data Index: 904394 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9768. Min Act: -0.0000

Data Index: 747651 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.0041. Min Act: -0.0001

Data Index: 767810 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9940. Min Act: -0.0000

Data Index: 568142 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.0151. Min Act: -0.0001

Data Index: 3632 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9856. Min Act: -0.0000

Data Index: 394304 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.0053. Min Act: -0.0000

Data Index: 98045 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9704. Min Act: -0.0000

Data Index: 99970 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9599. Min Act: -0.0000

Data Index: 642382 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9791. Min Act: -0.0001

Data Index: 897209 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9607. Min Act: -0.0000

Data Index: 105489 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9596. Min Act: -0.0001

Data Index: 821643 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1184633 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9851. Min Act: -0.0000

Data Index: 398464 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9291. Min Act: -0.0000

Data Index: 19083 (C4 (Web Text))

Max Activating Token Index: 216