Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1711. Min Act: -0.0001

Data Index: 581627 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1598. Min Act: -0.0001

Data Index: 76066 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1572. Min Act: -0.0001

Data Index: 679161 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1490. Min Act: -0.0001

Data Index: 733157 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1459. Min Act: -0.0001

Data Index: 303276 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1479. Min Act: -0.0001

Data Index: 586128 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1307. Min Act: -0.0001

Data Index: 167133 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1308468 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1385. Min Act: -0.0001

Data Index: 908609 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1276. Min Act: -0.0001

Data Index: 189630 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1249. Min Act: -0.0001

Data Index: 462878 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1260. Min Act: -0.0001

Data Index: 224434 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1334. Min Act: -0.0001

Data Index: 1007739 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1280. Min Act: -0.0001

Data Index: 984921 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1221. Min Act: -0.0001

Data Index: 737017 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1134. Min Act: -0.0001

Data Index: 23983 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1232. Min Act: -0.0001

Data Index: 563750 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1146. Min Act: -0.0001

Data Index: 34688 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1005458 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1064. Min Act: -0.0001

Data Index: 421946 (C4 (Web Text))

Max Activating Token Index: 213