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

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

Neuron 1107 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1354933 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2840. Min Act: -0.0001

Data Index: 774540 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2955. Min Act: -0.0001

Data Index: 198960 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2731. Min Act: -0.0001

Data Index: 630782 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2517. Min Act: -0.0001

Data Index: 454689 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2246. Min Act: -0.0001

Data Index: 545994 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2856. Min Act: -0.0001

Data Index: 1215206 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2646. Min Act: -0.0001

Data Index: 502580 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2300. Min Act: -0.0001

Data Index: 255431 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2755. Min Act: -0.0001

Data Index: 1130370 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2177. Min Act: -0.0001

Data Index: 446605 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2267. Min Act: -0.0001

Data Index: 391122 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2232. Min Act: -0.0001

Data Index: 70503 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2186. Min Act: -0.0001

Data Index: 848679 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2348. Min Act: -0.0001

Data Index: 763014 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2022. Min Act: -0.0001

Data Index: 147345 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2504. Min Act: -0.0001

Data Index: 741545 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2153. Min Act: -0.0001

Data Index: 344024 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2357. Min Act: -0.0001

Data Index: 351151 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1921. Min Act: -0.0001

Data Index: 65880 (C4 (Web Text))

Max Activating Token Index: 659