Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1145 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2238. Min Range: -2.2238

Max Act: 2.2238. Min Act: -0.0000

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 2.2238. Min Range: -2.2238

Max Act: 2.1401. Min Act: -0.0000

Data Index: 236063 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 2.2238. Min Range: -2.2238

Max Act: 2.0348. Min Act: -0.0000

Data Index: 1326491 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.8920. Min Act: -0.0000

Data Index: 784760 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.7712. Min Act: -0.0000

Data Index: 287982 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.8064. Min Act: 0.0000

Data Index: 253117 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.6773. Min Act: -0.0000

Data Index: 381076 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.7212. Min Act: -0.0000

Data Index: 210461 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1125227 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1160527 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1443390 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.4988. Min Act: -0.0000

Data Index: 1382198 (Python Code)

Max Activating Token Index: 374

Text #12

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.3868. Min Act: 0.0000

Data Index: 394441 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.3735. Min Act: 0.0000

Data Index: 1416634 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.3653. Min Act: -0.0000

Data Index: 970130 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1101860 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.4512. Min Act: 0.0000

Data Index: 365697 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.2235. Min Act: 0.0000

Data Index: 1376088 (Python Code)

Max Activating Token Index: 466

Text #18

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.4032. Min Act: 0.0000

Data Index: 1561351 (Python Code)

Max Activating Token Index: 834

Text #19

Max Range: 2.2238. Min Range: -2.2238

Max Act: 1.3955. Min Act: -0.0000

Data Index: 917552 (C4 (Web Text))

Max Activating Token Index: 618