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

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

Neuron 1097 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: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0006

Data Index: 353984 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0371. Min Act: -0.0006

Data Index: 611287 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0337. Min Act: -0.0006

Data Index: 1285048 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0327. Min Act: -0.0006

Data Index: 7366 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0270. Min Act: -0.0006

Data Index: 377363 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1029578 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0261. Min Act: -0.0006

Data Index: 928521 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0263. Min Act: -0.0006

Data Index: 926541 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0260. Min Act: -0.0006

Data Index: 35050 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1173555 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1135626 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0242. Min Act: -0.0006

Data Index: 237237 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0256. Min Act: -0.0006

Data Index: 197159 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0250. Min Act: -0.0006

Data Index: 458550 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0244. Min Act: -0.0006

Data Index: 103271 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0255. Min Act: -0.0006

Data Index: 392509 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0237. Min Act: -0.0006

Data Index: 458117 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0247. Min Act: -0.0006

Data Index: 283527 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0247. Min Act: -0.0006

Data Index: 594127 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0232. Min Act: -0.0006

Data Index: 355172 (C4 (Web Text))

Max Activating Token Index: 422