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

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

Neuron 2900 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: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0004

Data Index: 753882 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0337. Min Act: -0.0004

Data Index: 1154938 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0295. Min Act: -0.0004

Data Index: 367320 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0292. Min Act: -0.0004

Data Index: 736646 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0270. Min Act: -0.0004

Data Index: 162904 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0278. Min Act: -0.0004

Data Index: 1151338 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0281. Min Act: -0.0004

Data Index: 1234488 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0276. Min Act: -0.0004

Data Index: 196532 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0294. Min Act: -0.0004

Data Index: 156271 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0273. Min Act: -0.0004

Data Index: 2978 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0270. Min Act: -0.0004

Data Index: 1261493 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1072731 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0261. Min Act: -0.0004

Data Index: 1289629 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0244. Min Act: -0.0004

Data Index: 494243 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0298. Min Act: -0.0004

Data Index: 332154 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0230. Min Act: -0.0004

Data Index: 21767 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0204. Min Act: -0.0004

Data Index: 610634 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0290. Min Act: -0.0004

Data Index: 1098279 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0277. Min Act: -0.0004

Data Index: 313209 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0259. Min Act: -0.0004

Data Index: 176396 (C4 (Web Text))

Max Activating Token Index: 232