Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1828 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0006

Data Index: 364857 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0282. Min Act: -0.0006

Data Index: 184017 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0006

Data Index: 393340 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0281. Min Act: -0.0006

Data Index: 528321 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0280. Min Act: -0.0006

Data Index: 761805 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0278. Min Act: -0.0006

Data Index: 291025 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1190536 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0278. Min Act: -0.0006

Data Index: 545194 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0275. Min Act: -0.0006

Data Index: 956353 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1247571 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1026714 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1016137 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0277. Min Act: -0.0006

Data Index: 893840 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0276. Min Act: -0.0006

Data Index: 838432 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0275. Min Act: -0.0006

Data Index: 824663 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0268. Min Act: -0.0006

Data Index: 149914 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0263. Min Act: -0.0006

Data Index: 820601 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0273. Min Act: -0.0006

Data Index: 155755 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0267. Min Act: -0.0006

Data Index: 639049 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1259087 (C4 (Web Text))

Max Activating Token Index: 232