Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 26 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0444. Min Act: -0.0004

Data Index: 509138 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1208925 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0459. Min Act: -0.0003

Data Index: 526241 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0432. Min Act: -0.0004

Data Index: 1207418 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0428. Min Act: -0.0003

Data Index: 687430 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0423. Min Act: -0.0003

Data Index: 848975 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0433. Min Act: -0.0004

Data Index: 1061922 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0408. Min Act: -0.0003

Data Index: 71395 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1258001 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0400. Min Act: -0.0004

Data Index: 782471 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0397. Min Act: -0.0003

Data Index: 114977 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0405. Min Act: -0.0004

Data Index: 919630 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0410. Min Act: -0.0004

Data Index: 1049007 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0384. Min Act: -0.0004

Data Index: 357766 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1301819 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1767 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0384. Min Act: -0.0003

Data Index: 684002 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0397. Min Act: -0.0003

Data Index: 617895 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0384. Min Act: -0.0003

Data Index: 110618 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0360. Min Act: -0.0003

Data Index: 274517 (C4 (Web Text))

Max Activating Token Index: 571