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

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

Neuron 344 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: 4.2091. Min Range: -4.2091

Max Act: 4.2091. Min Act: -0.0001

Data Index: 14179 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.9206. Min Act: -0.0001

Data Index: 432619 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 4.2091. Min Range: -4.2091

Max Act: 4.0774. Min Act: -0.0001

Data Index: 1052997 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.7881. Min Act: -0.0001

Data Index: 298052 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.7644. Min Act: -0.0001

Data Index: 491408 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.6244. Min Act: -0.0001

Data Index: 499749 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.6061. Min Act: -0.0001

Data Index: 651369 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.7273. Min Act: -0.0000

Data Index: 1045325 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.2269. Min Act: -0.0001

Data Index: 676808 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.3549. Min Act: -0.0000

Data Index: 1208437 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.4187. Min Act: -0.0001

Data Index: 534937 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.9671. Min Act: -0.0001

Data Index: 598700 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.1454. Min Act: -0.0001

Data Index: 112583 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.1417. Min Act: -0.0001

Data Index: 561107 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 4.2091. Min Range: -4.2091

Max Act: 2.9844. Min Act: -0.0001

Data Index: 201126 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.0891. Min Act: -0.0001

Data Index: 882220 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 4.2091. Min Range: -4.2091

Max Act: 2.9684. Min Act: -0.0001

Data Index: 886813 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 4.2091. Min Range: -4.2091

Max Act: 2.9722. Min Act: -0.0001

Data Index: 296856 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 4.2091. Min Range: -4.2091

Max Act: 3.0831. Min Act: -0.0000

Data Index: 423112 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 4.2091. Min Range: -4.2091

Max Act: 2.7926. Min Act: -0.0001

Data Index: 831934 (C4 (Web Text))

Max Activating Token Index: 93