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

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

Neuron 3970 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: 1.4356. Min Range: -1.4356

Max Act: 1.4356. Min Act: -0.0002

Data Index: 689582 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.3868. Min Act: -0.0003

Data Index: 282559 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.3352. Min Act: -0.0002

Data Index: 207481 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.3263. Min Act: -0.0003

Data Index: 884079 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.3194. Min Act: -0.0002

Data Index: 927567 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.3107. Min Act: -0.0002

Data Index: 579987 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2921. Min Act: -0.0002

Data Index: 661756 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2766. Min Act: -0.0002

Data Index: 1352728 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2714. Min Act: -0.0003

Data Index: 982082 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2829. Min Act: -0.0002

Data Index: 399937 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2602. Min Act: -0.0002

Data Index: 441899 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2698. Min Act: -0.0002

Data Index: 557862 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2572. Min Act: -0.0002

Data Index: 905127 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2578. Min Act: -0.0002

Data Index: 853782 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2827. Min Act: -0.0002

Data Index: 720893 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2613. Min Act: -0.0002

Data Index: 626561 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2568. Min Act: -0.0003

Data Index: 713896 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2342. Min Act: -0.0002

Data Index: 560092 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2409. Min Act: -0.0002

Data Index: 81549 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.4356. Min Range: -1.4356

Max Act: 1.2342. Min Act: -0.0002

Data Index: 96746 (C4 (Web Text))

Max Activating Token Index: 214