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

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

Neuron 2579 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3139. Min Range: -3.3139

Max Act: 3.2102. Min Act: -0.0000

Data Index: 752250 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.3139. Min Range: -3.3139

Max Act: 3.3139. Min Act: -0.0000

Data Index: 1102612 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 3.3139. Min Range: -3.3139

Max Act: 3.2886. Min Act: -0.0000

Data Index: 1164093 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 3.3139. Min Range: -3.3139

Max Act: 3.0367. Min Act: -0.0000

Data Index: 667293 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 3.3139. Min Range: -3.3139

Max Act: 3.0165. Min Act: -0.0000

Data Index: 985992 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.7810. Min Act: -0.0000

Data Index: 1205636 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.4741. Min Act: -0.0000

Data Index: 200893 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.5692. Min Act: -0.0000

Data Index: 536322 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.3149. Min Act: -0.0000

Data Index: 368755 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.4227. Min Act: -0.0000

Data Index: 193944 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.3543. Min Act: -0.0000

Data Index: 495521 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.3377. Min Act: -0.0000

Data Index: 897043 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.4197. Min Act: -0.0000

Data Index: 127565 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.3912. Min Act: -0.0000

Data Index: 1048191 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.2710. Min Act: -0.0000

Data Index: 847559 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.1397. Min Act: -0.0000

Data Index: 414747 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.3701. Min Act: -0.0000

Data Index: 335698 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.3438. Min Act: -0.0000

Data Index: 312271 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.3283. Min Act: -0.0000

Data Index: 1121182 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 3.3139. Min Range: -3.3139

Max Act: 2.0522. Min Act: -0.0000

Data Index: 861953 (C4 (Web Text))

Max Activating Token Index: 750