Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3137 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.9484. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.6772. Min Act: -0.0000

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.9503. Min Act: -0.0000

Data Index: 1024561 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.7757. Min Act: -0.0000

Data Index: 986844 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8112. Min Act: -0.0000

Data Index: 6446 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.4815. Min Act: -0.0000

Data Index: 923468 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.2589. Min Act: -0.0000

Data Index: 665670 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1327135 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.0501. Min Act: -0.0000

Data Index: 410785 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.0860. Min Act: -0.0000

Data Index: 385240 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1094905 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.0083. Min Act: -0.0000

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 1.9503. Min Range: -1.9503

Max Act: 0.9895. Min Act: -0.0000

Data Index: 302495 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.9503. Min Range: -1.9503

Max Act: 0.9950. Min Act: -0.0000

Data Index: 528565 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.9503. Min Range: -1.9503

Max Act: 0.9227. Min Act: -0.0000

Data Index: 591478 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 1.9503. Min Range: -1.9503

Max Act: 0.9569. Min Act: -0.0000

Data Index: 867511 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 1.9503. Min Range: -1.9503

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1555264 (Python Code)

Max Activating Token Index: 86

Text #17

Max Range: 1.9503. Min Range: -1.9503

Max Act: 0.9170. Min Act: 0.0000

Data Index: 351943 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.9503. Min Range: -1.9503

Max Act: 0.8497. Min Act: -0.0000

Data Index: 994078 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.9503. Min Range: -1.9503

Max Act: 0.8984. Min Act: -0.0000

Data Index: 25426 (C4 (Web Text))

Max Activating Token Index: 908