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

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

Neuron 5990 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: 1.1352. Min Range: -1.1352

Max Act: 1.1352. Min Act: -0.0003

Data Index: 397321 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.1352. Min Range: -1.1352

Max Act: 1.0383. Min Act: -0.0002

Data Index: 540551 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.1352. Min Range: -1.1352

Max Act: 1.0158. Min Act: -0.0002

Data Index: 63456 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.1352. Min Range: -1.1352

Max Act: 1.0007. Min Act: -0.0003

Data Index: 252977 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9646. Min Act: -0.0002

Data Index: 1217329 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9750. Min Act: -0.0002

Data Index: 1048182 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9792. Min Act: -0.0002

Data Index: 33168 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9683. Min Act: -0.0002

Data Index: 931894 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9739. Min Act: -0.0002

Data Index: 606130 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9463. Min Act: -0.0002

Data Index: 183122 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9459. Min Act: -0.0002

Data Index: 339819 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9345. Min Act: -0.0002

Data Index: 1280996 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9229. Min Act: -0.0002

Data Index: 1225277 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9318. Min Act: -0.0002

Data Index: 182976 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9128. Min Act: -0.0002

Data Index: 283062 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9085. Min Act: -0.0002

Data Index: 768053 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9110. Min Act: -0.0002

Data Index: 236353 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9067. Min Act: -0.0002

Data Index: 488647 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.9146. Min Act: -0.0002

Data Index: 408248 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 1.1352. Min Range: -1.1352

Max Act: 0.8994. Min Act: -0.0003

Data Index: 1322152 (C4 (Web Text))

Max Activating Token Index: 605