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

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

Neuron 2460 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: 0.9776. Min Range: -0.9776

Max Act: 0.9776. Min Act: -0.0002

Data Index: 1014488 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.9245. Min Act: -0.0003

Data Index: 313261 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.9209. Min Act: -0.0002

Data Index: 105033 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8951. Min Act: -0.0002

Data Index: 651492 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8910. Min Act: -0.0002

Data Index: 718371 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8741. Min Act: -0.0002

Data Index: 1300243 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8615. Min Act: -0.0002

Data Index: 259022 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8385. Min Act: -0.0002

Data Index: 717036 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8519. Min Act: -0.0002

Data Index: 458703 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8589. Min Act: -0.0002

Data Index: 278390 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8448. Min Act: -0.0002

Data Index: 462056 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8458. Min Act: -0.0002

Data Index: 925566 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8381. Min Act: -0.0002

Data Index: 1041153 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8392. Min Act: -0.0002

Data Index: 57744 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8261. Min Act: -0.0002

Data Index: 610529 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8186. Min Act: -0.0002

Data Index: 443788 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8228. Min Act: -0.0002

Data Index: 15666 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8357. Min Act: -0.0002

Data Index: 134327 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8252. Min Act: -0.0002

Data Index: 773723 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8135. Min Act: -0.0002

Data Index: 661891 (C4 (Web Text))

Max Activating Token Index: 228