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

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

Neuron 632 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: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0003

Data Index: 750663 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1096042 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0363. Min Act: -0.0003

Data Index: 176160 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1358036 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0333. Min Act: -0.0003

Data Index: 107886 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0317. Min Act: -0.0002

Data Index: 792044 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1312631 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1030527 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0304. Min Act: -0.0003

Data Index: 242131 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0302. Min Act: -0.0003

Data Index: 863021 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0291. Min Act: -0.0003

Data Index: 71020 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0307. Min Act: -0.0004

Data Index: 1106924 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0292. Min Act: -0.0003

Data Index: 91593 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0291. Min Act: -0.0003

Data Index: 194837 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0288. Min Act: -0.0004

Data Index: 206056 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0282. Min Act: -0.0003

Data Index: 751642 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0261. Min Act: -0.0002

Data Index: 265143 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0295. Min Act: -0.0003

Data Index: 538715 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0273. Min Act: -0.0004

Data Index: 877149 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0288. Min Act: -0.0004

Data Index: 268487 (C4 (Web Text))

Max Activating Token Index: 386