Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 264 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0004

Data Index: 40659 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0332. Min Act: -0.0004

Data Index: 419895 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0386. Min Act: -0.0004

Data Index: 550307 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0337. Min Act: -0.0004

Data Index: 208096 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0355. Min Act: -0.0004

Data Index: 562378 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0386. Min Act: -0.0004

Data Index: 1031692 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0368. Min Act: -0.0004

Data Index: 440864 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0354. Min Act: -0.0004

Data Index: 555722 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0333. Min Act: -0.0004

Data Index: 623254 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0344. Min Act: -0.0004

Data Index: 816133 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0331. Min Act: -0.0004

Data Index: 1308535 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0336. Min Act: -0.0004

Data Index: 418810 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0336. Min Act: -0.0004

Data Index: 1165428 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0315. Min Act: -0.0004

Data Index: 516018 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0330. Min Act: -0.0004

Data Index: 93607 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0271. Min Act: -0.0004

Data Index: 464934 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1036220 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0316. Min Act: -0.0004

Data Index: 634445 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0305. Min Act: -0.0004

Data Index: 837923 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0322. Min Act: -0.0004

Data Index: 13039 (C4 (Web Text))

Max Activating Token Index: 903