Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1179 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.7321. Min Act: -0.0001

Data Index: 525525 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.7666. Min Act: -0.0001

Data Index: 472411 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 3.3570. Min Range: -3.3570

Max Act: 3.3570. Min Act: -0.0001

Data Index: 908513 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.4927. Min Act: -0.0001

Data Index: 140938 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.2268. Min Act: -0.0001

Data Index: 1218103 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.4199. Min Act: -0.0001

Data Index: 358097 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.5210. Min Act: -0.0001

Data Index: 808961 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.2286. Min Act: -0.0001

Data Index: 577590 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.3287. Min Act: -0.0001

Data Index: 453734 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.1133. Min Act: -0.0001

Data Index: 435244 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.2195. Min Act: -0.0001

Data Index: 729643 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.1091. Min Act: -0.0001

Data Index: 171021 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.3570. Min Range: -3.3570

Max Act: 1.8739. Min Act: -0.0001

Data Index: 244089 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.0105. Min Act: -0.0001

Data Index: 757064 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 3.3570. Min Range: -3.3570

Max Act: 1.9738. Min Act: -0.0000

Data Index: 378799 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.0465. Min Act: -0.0001

Data Index: 1039166 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.1412. Min Act: -0.0001

Data Index: 937171 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 3.3570. Min Range: -3.3570

Max Act: 2.2476. Min Act: -0.0001

Data Index: 174423 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 3.3570. Min Range: -3.3570

Max Act: 1.9996. Min Act: -0.0001

Data Index: 1165468 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 3.3570. Min Range: -3.3570

Max Act: 1.9943. Min Act: -0.0001

Data Index: 156056 (C4 (Web Text))

Max Activating Token Index: 1014