Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 541 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4874. Min Act: -0.0001

Data Index: 222789 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4198. Min Act: -0.0000

Data Index: 1109621 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3613. Min Act: -0.0000

Data Index: 508862 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.2611. Min Act: -0.0000

Data Index: 282397 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.2612. Min Act: -0.0000

Data Index: 195633 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.2419. Min Act: -0.0000

Data Index: 500977 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.2355. Min Act: -0.0000

Data Index: 1270293 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.2019. Min Act: -0.0000

Data Index: 204937 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.9616. Min Act: -0.0000

Data Index: 757463 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.0413. Min Act: -0.0001

Data Index: 189235 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.1406. Min Act: -0.0000

Data Index: 641110 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.0320. Min Act: -0.0000

Data Index: 1290633 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.9812. Min Act: -0.0000

Data Index: 87341 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.9795. Min Act: -0.0001

Data Index: 1023175 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.9549. Min Act: -0.0001

Data Index: 1080364 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.9534. Min Act: -0.0000

Data Index: 1206145 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.9573. Min Act: -0.0000

Data Index: 141396 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.7646. Min Act: -0.0000

Data Index: 1036573 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.8412. Min Act: -0.0000

Data Index: 129108 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 2.4874. Min Range: -2.4874

Max Act: 1.8366. Min Act: -0.0000

Data Index: 876232 (C4 (Web Text))

Max Activating Token Index: 42