Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1549 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0829. Min Act: -0.0002

Data Index: 477108 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0856. Min Act: -0.0002

Data Index: 1254919 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0538. Min Act: -0.0002

Data Index: 336987 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0481. Min Act: -0.0002

Data Index: 1260765 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0364. Min Act: -0.0002

Data Index: 368919 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0484. Min Act: -0.0002

Data Index: 341859 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0287. Min Act: -0.0002

Data Index: 580751 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0316. Min Act: -0.0003

Data Index: 1312360 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0274. Min Act: -0.0002

Data Index: 1068397 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0120. Min Act: -0.0002

Data Index: 448794 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0177. Min Act: -0.0003

Data Index: 620676 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0082. Min Act: -0.0002

Data Index: 1280578 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0089. Min Act: -0.0003

Data Index: 1268600 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0140. Min Act: -0.0003

Data Index: 561640 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0049. Min Act: -0.0002

Data Index: 1081850 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0050. Min Act: -0.0002

Data Index: 1314733 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9989. Min Act: -0.0003

Data Index: 1143661 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9813. Min Act: -0.0003

Data Index: 1232707 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0191. Min Act: -0.0002

Data Index: 1324193 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9949. Min Act: -0.0002

Data Index: 1288406 (C4 (Web Text))

Max Activating Token Index: 576