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

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

Neuron 4829 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0625. Min Range: -1.0625

Max Act: 1.0625. Min Act: -0.0000

Data Index: 318991 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.0625. Min Range: -1.0625

Max Act: 1.0089. Min Act: -0.0000

Data Index: 305415 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1223817 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8687. Min Act: -0.0000

Data Index: 332213 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1095514 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8911. Min Act: -0.0000

Data Index: 72255 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.9140. Min Act: -0.0000

Data Index: 210781 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8828. Min Act: -0.0000

Data Index: 326828 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8914. Min Act: -0.0000

Data Index: 58915 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8618. Min Act: -0.0000

Data Index: 955265 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8557. Min Act: -0.0000

Data Index: 341471 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8751. Min Act: -0.0000

Data Index: 506162 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1026846 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1203553 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1008253 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1202577 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1293546 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8063. Min Act: -0.0000

Data Index: 367431 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.7929. Min Act: -0.0000

Data Index: 870996 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.0625. Min Range: -1.0625

Max Act: 0.8374. Min Act: -0.0000

Data Index: 4100 (C4 (Web Text))

Max Activating Token Index: 269