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

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

Neuron 1702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1286. Min Range: -4.1286

Max Act: 4.1286. Min Act: -0.0000

Data Index: 395301 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.5497. Min Act: -0.0000

Data Index: 1273229 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.4061. Min Act: -0.0000

Data Index: 210839 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.2770. Min Act: -0.0000

Data Index: 251873 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.0654. Min Act: -0.0000

Data Index: 1215206 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.0548. Min Act: -0.0000

Data Index: 36655 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.1744. Min Act: -0.0000

Data Index: 932022 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.1388. Min Act: -0.0000

Data Index: 757885 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.9415. Min Act: -0.0000

Data Index: 603015 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.0800. Min Act: -0.0000

Data Index: 863448 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.9240. Min Act: -0.0000

Data Index: 601513 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.5517. Min Act: -0.0000

Data Index: 534 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.9136. Min Act: -0.0000

Data Index: 1091743 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.7564. Min Act: -0.0000

Data Index: 1348462 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.6129. Min Act: -0.0000

Data Index: 3718 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.7376. Min Act: -0.0000

Data Index: 656446 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.6939. Min Act: -0.0000

Data Index: 706868 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.5093. Min Act: -0.0000

Data Index: 854353 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.5162. Min Act: -0.0000

Data Index: 709316 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 4.1286. Min Range: -4.1286

Max Act: 2.5854. Min Act: -0.0000

Data Index: 446406 (C4 (Web Text))

Max Activating Token Index: 803