Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1815 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0463. Min Act: -0.0006

Data Index: 490875 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0303. Min Act: -0.0006

Data Index: 67665 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1101790 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1293082 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0273. Min Act: -0.0006

Data Index: 154913 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0277. Min Act: -0.0005

Data Index: 957835 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0262. Min Act: -0.0006

Data Index: 142673 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1333435 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0262. Min Act: -0.0005

Data Index: 232522 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0273. Min Act: -0.0006

Data Index: 930544 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1259249 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1194091 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0267. Min Act: -0.0006

Data Index: 392431 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0272. Min Act: -0.0006

Data Index: 936319 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0259. Min Act: -0.0005

Data Index: 933973 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0276. Min Act: -0.0005

Data Index: 359164 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1205946 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0267. Min Act: -0.0006

Data Index: 789221 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0260. Min Act: -0.0006

Data Index: 391 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0254. Min Act: -0.0006

Data Index: 548940 (C4 (Web Text))

Max Activating Token Index: 875