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

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

Neuron 509 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: 5.5151. Min Range: -5.5151

Max Act: 5.5151. Min Act: -0.0002

Data Index: 140281 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.6394. Min Act: -0.0002

Data Index: 513035 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.5523. Min Act: -0.0002

Data Index: 323241 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.3596. Min Act: -0.0002

Data Index: 403057 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.2226. Min Act: -0.0002

Data Index: 237236 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.2793. Min Act: -0.0002

Data Index: 223686 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.1602. Min Act: -0.0002

Data Index: 634174 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.2279. Min Act: -0.0002

Data Index: 477622 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.1818. Min Act: -0.0002

Data Index: 622482 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.0884. Min Act: -0.0002

Data Index: 798002 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.0383. Min Act: -0.0002

Data Index: 635783 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 5.5151. Min Range: -5.5151

Max Act: 3.9894. Min Act: -0.0002

Data Index: 383329 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 5.5151. Min Range: -5.5151

Max Act: 4.0317. Min Act: -0.0002

Data Index: 371351 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 5.5151. Min Range: -5.5151

Max Act: 3.9632. Min Act: -0.0002

Data Index: 1201759 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 5.5151. Min Range: -5.5151

Max Act: 3.9168. Min Act: -0.0002

Data Index: 170331 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 5.5151. Min Range: -5.5151

Max Act: 3.8571. Min Act: -0.0002

Data Index: 425155 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 5.5151. Min Range: -5.5151

Max Act: 3.8017. Min Act: -0.0002

Data Index: 765307 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 5.5151. Min Range: -5.5151

Max Act: 3.7797. Min Act: -0.0002

Data Index: 1235669 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 5.5151. Min Range: -5.5151

Max Act: 3.7821. Min Act: -0.0002

Data Index: 589807 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 5.5151. Min Range: -5.5151

Max Act: 3.7329. Min Act: -0.0002

Data Index: 196419 (C4 (Web Text))

Max Activating Token Index: 302