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

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

Neuron 93 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: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1199327 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1009949 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0426. Min Act: -0.0003

Data Index: 764181 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1025735 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0409. Min Act: -0.0002

Data Index: 638378 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0392. Min Act: -0.0002

Data Index: 57120 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1099975 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0362. Min Act: -0.0003

Data Index: 869788 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0348. Min Act: -0.0002

Data Index: 13556 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0344. Min Act: -0.0002

Data Index: 995464 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0355. Min Act: -0.0003

Data Index: 318538 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1000455 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0323. Min Act: -0.0002

Data Index: 489902 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0319. Min Act: -0.0002

Data Index: 502390 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0325. Min Act: -0.0002

Data Index: 322065 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0312. Min Act: -0.0002

Data Index: 702097 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0304. Min Act: -0.0002

Data Index: 420479 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0303. Min Act: -0.0002

Data Index: 91070 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0306. Min Act: -0.0002

Data Index: 947595 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1122321 (C4 (Web Text))

Max Activating Token Index: 46