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

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

Neuron 3731 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: 0.1590. Min Range: -0.1590

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1134234 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1131437 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1271848 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1283. Min Act: -0.0001

Data Index: 993763 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1101089 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1246. Min Act: -0.0001

Data Index: 22974 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1209. Min Act: -0.0001

Data Index: 780745 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1080. Min Act: -0.0001

Data Index: 50063 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1122. Min Act: -0.0001

Data Index: 698226 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1150. Min Act: -0.0001

Data Index: 579719 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1254002 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1000. Min Act: -0.0001

Data Index: 134234 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1116. Min Act: -0.0001

Data Index: 972628 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1090. Min Act: -0.0001

Data Index: 334594 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.0970. Min Act: -0.0001

Data Index: 650865 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1027. Min Act: -0.0001

Data Index: 377595 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.0953. Min Act: -0.0001

Data Index: 832932 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1164291 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.0952. Min Act: -0.0001

Data Index: 984162 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.1590. Min Range: -0.1590

Max Act: 0.0975. Min Act: -0.0001

Data Index: 159968 (C4 (Web Text))

Max Activating Token Index: 767