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

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

Neuron 836 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.5285. Min Act: -0.0000

Data Index: 1291171 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.1854. Min Act: -0.0000

Data Index: 787258 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.2014. Min Act: -0.0000

Data Index: 1018926 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.0450. Min Act: -0.0000

Data Index: 876663 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.1410. Min Act: -0.0000

Data Index: 440003 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.2082. Min Act: -0.0000

Data Index: 34089 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.0054. Min Act: -0.0000

Data Index: 760056 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9967. Min Act: -0.0001

Data Index: 511351 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9487. Min Act: -0.0000

Data Index: 509839 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9746. Min Act: -0.0001

Data Index: 60658 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.0140. Min Act: -0.0001

Data Index: 371408 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9583. Min Act: -0.0001

Data Index: 199146 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9609. Min Act: -0.0001

Data Index: 890538 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.5285. Min Range: -1.5285

Max Act: 1.0080. Min Act: -0.0001

Data Index: 564530 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9723. Min Act: -0.0000

Data Index: 481317 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9419. Min Act: -0.0000

Data Index: 716177 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9918. Min Act: -0.0000

Data Index: 127190 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1316283 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9755. Min Act: -0.0001

Data Index: 474641 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 1.5285. Min Range: -1.5285

Max Act: 0.9989. Min Act: -0.0001

Data Index: 695745 (C4 (Web Text))

Max Activating Token Index: 389