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

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

Neuron 2828 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0348. Min Act: -0.0003

Data Index: 219654 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1010875 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1061792 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0324. Min Act: -0.0003

Data Index: 874040 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0296. Min Act: -0.0003

Data Index: 406789 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0293. Min Act: -0.0003

Data Index: 219120 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1485867 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1592673 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0277. Min Act: -0.0003

Data Index: 744908 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1259712 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1424485 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0257. Min Act: -0.0003

Data Index: 244040 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1302163 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0268. Min Act: -0.0003

Data Index: 854740 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1341642 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1081959 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1612926 (Python Code)

Max Activating Token Index: 314

Text #17

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1217054 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1513572 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0282. Min Act: -0.0003

Data Index: 373376 (C4 (Web Text))

Max Activating Token Index: 402