Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 657 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.9248. Min Act: -0.0001

Data Index: 969536 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.9152. Min Act: -0.0001

Data Index: 401715 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8699. Min Act: -0.0001

Data Index: 135677 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8409. Min Act: -0.0000

Data Index: 192478 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8663. Min Act: -0.0000

Data Index: 147142 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8354. Min Act: -0.0001

Data Index: 867690 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8027. Min Act: -0.0000

Data Index: 357193 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8363. Min Act: -0.0001

Data Index: 970402 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7929. Min Act: -0.0000

Data Index: 86636 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8685. Min Act: -0.0001

Data Index: 290203 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8139. Min Act: -0.0001

Data Index: 428483 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8379. Min Act: -0.0001

Data Index: 720231 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8077. Min Act: -0.0001

Data Index: 673700 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1257989 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8240. Min Act: -0.0001

Data Index: 182473 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8165. Min Act: -0.0001

Data Index: 291242 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8157. Min Act: -0.0001

Data Index: 339966 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7566. Min Act: -0.0001

Data Index: 325232 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7846. Min Act: -0.0001

Data Index: 538519 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7498. Min Act: -0.0001

Data Index: 505438 (C4 (Web Text))

Max Activating Token Index: 893