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

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

Neuron 2030 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2455. Min Act: -0.0001

Data Index: 38833 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2109. Min Act: -0.0001

Data Index: 1197090 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1515. Min Act: -0.0001

Data Index: 355826 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1585. Min Act: -0.0001

Data Index: 770820 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1520. Min Act: -0.0001

Data Index: 207051 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1399. Min Act: -0.0001

Data Index: 443050 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1410. Min Act: -0.0001

Data Index: 31582 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1243. Min Act: -0.0001

Data Index: 91892 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1464. Min Act: -0.0001

Data Index: 980137 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1261. Min Act: -0.0001

Data Index: 568478 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1513. Min Act: -0.0001

Data Index: 73181 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1227. Min Act: -0.0001

Data Index: 939063 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1363. Min Act: -0.0001

Data Index: 118380 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1290. Min Act: -0.0001

Data Index: 49877 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1367. Min Act: -0.0001

Data Index: 809097 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1456. Min Act: -0.0001

Data Index: 725363 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1275. Min Act: -0.0001

Data Index: 646976 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1305. Min Act: -0.0001

Data Index: 220248 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1298. Min Act: -0.0001

Data Index: 143739 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1253. Min Act: -0.0001

Data Index: 846158 (C4 (Web Text))

Max Activating Token Index: 257