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

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

Neuron 382 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: 0.7157. Min Range: -0.7157

Max Act: 0.7157. Min Act: 0.0000

Data Index: 887373 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6294. Min Act: -0.0001

Data Index: 44746 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1251940 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6742. Min Act: -0.0000

Data Index: 695747 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6625. Min Act: -0.0001

Data Index: 505296 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6469. Min Act: -0.0000

Data Index: 469229 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6451. Min Act: -0.0001

Data Index: 147315 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.6374. Min Act: -0.0001

Data Index: 97388 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1087166 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1273367 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1157579 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5127. Min Act: -0.0000

Data Index: 416606 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5319. Min Act: -0.0000

Data Index: 225287 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5241. Min Act: -0.0001

Data Index: 1222897 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4885. Min Act: -0.0001

Data Index: 990656 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.5132. Min Act: -0.0001

Data Index: 968518 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4889. Min Act: -0.0001

Data Index: 580320 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4914. Min Act: -0.0000

Data Index: 635357 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4806. Min Act: -0.0001

Data Index: 291220 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.7157. Min Range: -0.7157

Max Act: 0.4873. Min Act: -0.0001

Data Index: 1309586 (C4 (Web Text))

Max Activating Token Index: 65