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

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

Neuron 1096 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: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: -0.0004

Data Index: 447321 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1427491 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0316. Min Act: -0.0003

Data Index: 767094 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0329. Min Act: -0.0003

Data Index: 129755 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0328. Min Act: -0.0003

Data Index: 993887 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0331. Min Act: -0.0003

Data Index: 66642 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0330. Min Act: -0.0003

Data Index: 303729 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0316. Min Act: -0.0003

Data Index: 200861 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0322. Min Act: -0.0002

Data Index: 111500 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0318. Min Act: -0.0004

Data Index: 47374 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1530126 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0314. Min Act: -0.0002

Data Index: 346523 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1205119 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1063761 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0317. Min Act: -0.0003

Data Index: 689008 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0307. Min Act: -0.0002

Data Index: 615429 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1447676 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1441427 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1413887 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1084257 (C4 (Web Text))

Max Activating Token Index: 527