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

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

Neuron 5696 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: 2.1658. Min Range: -2.1658

Max Act: 2.1658. Min Act: -0.0002

Data Index: 630909 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 2.1658. Min Range: -2.1658

Max Act: 2.0317. Min Act: -0.0002

Data Index: 13043 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.9401. Min Act: -0.0002

Data Index: 1003596 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.9047. Min Act: -0.0002

Data Index: 565967 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.7855. Min Act: -0.0003

Data Index: 999425 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.7306. Min Act: -0.0002

Data Index: 970445 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.7093. Min Act: -0.0003

Data Index: 1151874 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.7162. Min Act: -0.0002

Data Index: 442174 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5838. Min Act: -0.0002

Data Index: 772930 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5496. Min Act: -0.0002

Data Index: 77660 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5335. Min Act: -0.0002

Data Index: 390021 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5063. Min Act: -0.0002

Data Index: 715430 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5460. Min Act: -0.0002

Data Index: 471139 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5543. Min Act: -0.0003

Data Index: 1275442 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.4930. Min Act: -0.0002

Data Index: 1015671 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5007. Min Act: -0.0002

Data Index: 506553 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.4962. Min Act: -0.0002

Data Index: 763192 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.4789. Min Act: -0.0002

Data Index: 916359 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.4667. Min Act: -0.0003

Data Index: 752153 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.4847. Min Act: -0.0002

Data Index: 1344728 (C4 (Web Text))

Max Activating Token Index: 845