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

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

Neuron 2104 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1537. Min Act: -0.0001

Data Index: 329751 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1027301 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1472. Min Act: -0.0001

Data Index: 820824 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1064536 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1338. Min Act: -0.0001

Data Index: 33221 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1157186 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1213. Min Act: -0.0001

Data Index: 194078 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1296267 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1256. Min Act: -0.0001

Data Index: 744769 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1280. Min Act: -0.0001

Data Index: 509278 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1314. Min Act: -0.0001

Data Index: 683370 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1065651 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1238. Min Act: -0.0001

Data Index: 449870 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1208. Min Act: -0.0001

Data Index: 589983 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1234. Min Act: -0.0001

Data Index: 611991 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1202. Min Act: -0.0001

Data Index: 712249 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1249. Min Act: -0.0001

Data Index: 156413 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1147. Min Act: -0.0001

Data Index: 27942 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1288. Min Act: -0.0001

Data Index: 765235 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1234. Min Act: -0.0001

Data Index: 416497 (C4 (Web Text))

Max Activating Token Index: 109