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

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

Neuron 391 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0530. Min Range: -1.0530

Max Act: 1.0530. Min Act: -0.0001

Data Index: 958469 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.9777. Min Act: -0.0000

Data Index: 919210 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.9583. Min Act: -0.0000

Data Index: 318626 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.9411. Min Act: -0.0001

Data Index: 217562 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.9045. Min Act: -0.0001

Data Index: 477664 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.8207. Min Act: -0.0000

Data Index: 292268 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.7843. Min Act: -0.0001

Data Index: 1290040 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.8296. Min Act: -0.0001

Data Index: 982511 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.8033. Min Act: -0.0001

Data Index: 199673 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1213933 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.8025. Min Act: -0.0001

Data Index: 493192 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.7715. Min Act: -0.0001

Data Index: 537285 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.8114. Min Act: -0.0001

Data Index: 683066 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.8105. Min Act: -0.0001

Data Index: 593532 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.7751. Min Act: -0.0001

Data Index: 758226 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.7748. Min Act: -0.0001

Data Index: 494294 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.7466. Min Act: -0.0001

Data Index: 19990 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.7472. Min Act: -0.0001

Data Index: 1071139 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.7462. Min Act: -0.0001

Data Index: 1320139 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 1.0530. Min Range: -1.0530

Max Act: 0.7383. Min Act: -0.0001

Data Index: 1028820 (C4 (Web Text))

Max Activating Token Index: 272