Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3845 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.7267. Min Act: -0.0001

Data Index: 1034944 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.5504. Min Act: -0.0001

Data Index: 428180 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.4465. Min Act: -0.0001

Data Index: 231188 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.4557. Min Act: -0.0001

Data Index: 348921 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.4509. Min Act: -0.0001

Data Index: 1247021 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.4920. Min Act: -0.0001

Data Index: 193560 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.4315. Min Act: -0.0001

Data Index: 752273 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.2336. Min Act: -0.0001

Data Index: 603836 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.3258. Min Act: -0.0001

Data Index: 1241450 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.1187. Min Act: -0.0001

Data Index: 1051658 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.1782. Min Act: -0.0001

Data Index: 298380 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.2298. Min Act: -0.0001

Data Index: 1188114 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.3489. Min Act: -0.0001

Data Index: 1302661 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.3496. Min Act: -0.0001

Data Index: 752303 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.2916. Min Act: -0.0001

Data Index: 189167 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.3721. Min Act: -0.0001

Data Index: 108754 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.1778. Min Act: -0.0001

Data Index: 163752 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.1772. Min Act: -0.0001

Data Index: 851619 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.2889. Min Act: -0.0001

Data Index: 1195362 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.7267. Min Range: -1.7267

Max Act: 1.1275. Min Act: -0.0001

Data Index: 463514 (C4 (Web Text))

Max Activating Token Index: 976