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

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

Neuron 4523 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: 1.1652. Min Range: -1.1652

Max Act: 1.1652. Min Act: -0.0003

Data Index: 1048999 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.1013. Min Act: -0.0002

Data Index: 1254164 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0860. Min Act: -0.0002

Data Index: 635362 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0929. Min Act: -0.0002

Data Index: 846603 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0875. Min Act: -0.0002

Data Index: 664334 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0561. Min Act: -0.0002

Data Index: 1343729 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0656. Min Act: -0.0003

Data Index: 906840 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0804. Min Act: -0.0003

Data Index: 813464 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0572. Min Act: -0.0002

Data Index: 218603 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0395. Min Act: -0.0002

Data Index: 222864 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0472. Min Act: -0.0002

Data Index: 563130 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0593. Min Act: -0.0002

Data Index: 242067 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0643. Min Act: -0.0002

Data Index: 500898 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0662. Min Act: -0.0002

Data Index: 252740 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0369. Min Act: -0.0002

Data Index: 1105848 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0322. Min Act: -0.0002

Data Index: 611568 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0480. Min Act: -0.0002

Data Index: 690896 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0186. Min Act: -0.0002

Data Index: 127815 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0289. Min Act: -0.0002

Data Index: 96567 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.1652. Min Range: -1.1652

Max Act: 1.0134. Min Act: -0.0002

Data Index: 1035455 (C4 (Web Text))

Max Activating Token Index: 532