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

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

Neuron 2675 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.3285. Min Act: -0.0002

Data Index: 955935 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.1882. Min Act: -0.0001

Data Index: 56714 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.9691. Min Act: -0.0002

Data Index: 1241511 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 3.3285. Min Range: -3.3285

Max Act: 3.0798. Min Act: -0.0002

Data Index: 1251529 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.8370. Min Act: -0.0001

Data Index: 107275 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.8415. Min Act: -0.0002

Data Index: 268786 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.8288. Min Act: -0.0002

Data Index: 39112 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.8091. Min Act: -0.0001

Data Index: 45013 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.8177. Min Act: -0.0002

Data Index: 858503 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.6818. Min Act: -0.0002

Data Index: 1067536 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.5051. Min Act: -0.0002

Data Index: 1293413 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.7488. Min Act: -0.0001

Data Index: 415202 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.5437. Min Act: -0.0002

Data Index: 1040225 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.7085. Min Act: -0.0001

Data Index: 1233953 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.8362. Min Act: -0.0001

Data Index: 522357 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.7097. Min Act: -0.0001

Data Index: 476564 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.7025. Min Act: -0.0002

Data Index: 739610 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.5559. Min Act: -0.0002

Data Index: 277575 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.5456. Min Act: -0.0001

Data Index: 492074 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.3285. Min Range: -3.3285

Max Act: 2.5365. Min Act: -0.0001

Data Index: 733344 (C4 (Web Text))

Max Activating Token Index: 99