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

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

Neuron 760 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.5562. Min Act: -0.0001

Data Index: 715723 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.5375. Min Act: -0.0001

Data Index: 1011322 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.4543. Min Act: -0.0001

Data Index: 1280647 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.4302. Min Act: -0.0001

Data Index: 271836 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3854. Min Act: -0.0001

Data Index: 1316117 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3663. Min Act: -0.0001

Data Index: 429365 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.4109. Min Act: -0.0001

Data Index: 1164348 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3195. Min Act: -0.0001

Data Index: 357293 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3239. Min Act: -0.0001

Data Index: 342533 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.4635. Min Act: -0.0001

Data Index: 851205 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3925. Min Act: -0.0001

Data Index: 239582 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3135. Min Act: -0.0001

Data Index: 854654 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2678. Min Act: -0.0001

Data Index: 1337673 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3116. Min Act: -0.0001

Data Index: 740407 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3174. Min Act: -0.0001

Data Index: 534101 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3160. Min Act: -0.0001

Data Index: 1037962 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3100. Min Act: -0.0001

Data Index: 293381 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3119. Min Act: -0.0001

Data Index: 633944 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2316. Min Act: -0.0001

Data Index: 166516 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2295. Min Act: -0.0001

Data Index: 242302 (C4 (Web Text))

Max Activating Token Index: 610