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

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

Neuron 4067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.5894. Min Act: -0.0001

Data Index: 562569 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.5329. Min Act: -0.0001

Data Index: 350943 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.4324. Min Act: -0.0001

Data Index: 593818 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.3139. Min Act: -0.0001

Data Index: 370852 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.4294. Min Act: -0.0001

Data Index: 641253 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2617. Min Act: -0.0001

Data Index: 80644 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.3328. Min Act: -0.0001

Data Index: 175865 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2221. Min Act: -0.0001

Data Index: 1080241 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1906. Min Act: -0.0001

Data Index: 1241018 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2794. Min Act: -0.0001

Data Index: 994756 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2500. Min Act: -0.0001

Data Index: 874985 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1631. Min Act: -0.0001

Data Index: 1316421 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2412. Min Act: -0.0001

Data Index: 551368 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1719. Min Act: -0.0001

Data Index: 234509 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1541. Min Act: -0.0001

Data Index: 1235318 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1675. Min Act: -0.0001

Data Index: 226651 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1557. Min Act: -0.0001

Data Index: 1222825 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0858. Min Act: -0.0001

Data Index: 45736 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1320. Min Act: -0.0001

Data Index: 1349354 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0945. Min Act: -0.0001

Data Index: 32841 (C4 (Web Text))

Max Activating Token Index: 236