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

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

Neuron 2076 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: 2.0463. Min Range: -2.0463

Max Act: 2.0463. Min Act: -0.0000

Data Index: 614567 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 2.0463. Min Range: -2.0463

Max Act: 2.0413. Min Act: -0.0000

Data Index: 21387 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.8413. Min Act: -0.0000

Data Index: 221397 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.8503. Min Act: -0.0000

Data Index: 1143765 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7476. Min Act: -0.0000

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.6504. Min Act: -0.0000

Data Index: 1125380 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7721. Min Act: -0.0000

Data Index: 876164 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.5758. Min Act: -0.0000

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.5061. Min Act: -0.0000

Data Index: 386331 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.5613. Min Act: -0.0001

Data Index: 526374 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.4971. Min Act: -0.0001

Data Index: 546241 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.5495. Min Act: -0.0000

Data Index: 780411 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.4737. Min Act: -0.0001

Data Index: 950752 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.3281. Min Act: -0.0000

Data Index: 720804 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.3026. Min Act: -0.0000

Data Index: 239436 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.2384. Min Act: -0.0001

Data Index: 433494 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.2918. Min Act: -0.0001

Data Index: 450041 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.2249. Min Act: -0.0001

Data Index: 169664 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1314685 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.1863. Min Act: -0.0000

Data Index: 966195 (C4 (Web Text))

Max Activating Token Index: 694