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

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

Neuron 5184 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7448. Min Range: -5.7448

Max Act: 5.5750. Min Act: -0.0001

Data Index: 615778 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 5.7448. Min Range: -5.7448

Max Act: 5.7448. Min Act: -0.0001

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 5.7448. Min Range: -5.7448

Max Act: 5.1043. Min Act: -0.0001

Data Index: 998845 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 5.7448. Min Range: -5.7448

Max Act: 5.0228. Min Act: -0.0001

Data Index: 449246 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 5.7448. Min Range: -5.7448

Max Act: 4.0906. Min Act: -0.0001

Data Index: 655892 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 5.7448. Min Range: -5.7448

Max Act: 4.2590. Min Act: -0.0001

Data Index: 1217258 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 5.7448. Min Range: -5.7448

Max Act: 4.0464. Min Act: -0.0001

Data Index: 505285 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 5.7448. Min Range: -5.7448

Max Act: 4.5325. Min Act: -0.0001

Data Index: 452464 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 5.7448. Min Range: -5.7448

Max Act: 4.1944. Min Act: -0.0001

Data Index: 428573 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.8543. Min Act: -0.0001

Data Index: 584902 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.9644. Min Act: -0.0001

Data Index: 878141 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.9823. Min Act: -0.0001

Data Index: 474267 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 5.7448. Min Range: -5.7448

Max Act: 4.0724. Min Act: -0.0001

Data Index: 726328 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.7784. Min Act: -0.0001

Data Index: 1003913 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.5793. Min Act: -0.0001

Data Index: 413230 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.8961. Min Act: -0.0001

Data Index: 1275136 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.7217. Min Act: -0.0001

Data Index: 1103818 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.8189. Min Act: -0.0001

Data Index: 252337 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.4973. Min Act: -0.0001

Data Index: 896499 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 5.7448. Min Range: -5.7448

Max Act: 3.5041. Min Act: -0.0001

Data Index: 1191505 (C4 (Web Text))

Max Activating Token Index: 491