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

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

Neuron 1531 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.9712. Min Act: -0.0000

Data Index: 373880 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.8353. Min Act: -0.0000

Data Index: 322417 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.5470. Min Act: -0.0000

Data Index: 19501 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.3771. Min Act: -0.0000

Data Index: 1056049 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.3730. Min Act: -0.0000

Data Index: 1317073 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.4923. Min Act: -0.0000

Data Index: 479079 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.0591. Min Act: -0.0000

Data Index: 1113047 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.1585. Min Act: -0.0000

Data Index: 1237177 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.3400. Min Act: -0.0000

Data Index: 915191 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 2.9712. Min Range: -2.9712

Max Act: 2.0392. Min Act: -0.0000

Data Index: 403367 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.9238. Min Act: -0.0000

Data Index: 918060 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.8867. Min Act: -0.0000

Data Index: 6836 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.8826. Min Act: -0.0000

Data Index: 958950 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.9638. Min Act: -0.0000

Data Index: 1212139 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.9294. Min Act: -0.0000

Data Index: 728338 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.9225. Min Act: -0.0000

Data Index: 308017 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.6935. Min Act: -0.0000

Data Index: 1012934 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.7550. Min Act: -0.0000

Data Index: 46434 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1250622 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 2.9712. Min Range: -2.9712

Max Act: 1.8266. Min Act: -0.0000

Data Index: 301004 (C4 (Web Text))

Max Activating Token Index: 605