Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1980 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1342426 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0342. Min Act: -0.0003

Data Index: 92260 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0268. Min Act: -0.0002

Data Index: 328558 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0269. Min Act: -0.0002

Data Index: 183745 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0269. Min Act: -0.0003

Data Index: 9391 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0265. Min Act: -0.0002

Data Index: 297552 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0253. Min Act: -0.0004

Data Index: 73688 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0251. Min Act: -0.0003

Data Index: 873004 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0267. Min Act: -0.0003

Data Index: 592235 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0240. Min Act: -0.0003

Data Index: 565870 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0260. Min Act: -0.0003

Data Index: 943934 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0232. Min Act: -0.0003

Data Index: 596333 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1303197 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0242. Min Act: -0.0003

Data Index: 998048 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0232. Min Act: -0.0004

Data Index: 523007 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1047425 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1308348 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1228858 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1293968 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1135963 (C4 (Web Text))

Max Activating Token Index: 231