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

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

Neuron 3658 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.4443. Min Act: -0.0001

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.1099. Min Act: -0.0001

Data Index: 291558 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.1461. Min Act: -0.0001

Data Index: 258820 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.1002. Min Act: -0.0001

Data Index: 611599 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1335055 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0217. Min Act: -0.0001

Data Index: 1228224 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0562. Min Act: -0.0001

Data Index: 102004 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0225. Min Act: -0.0001

Data Index: 734597 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0128. Min Act: -0.0001

Data Index: 891170 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0618. Min Act: -0.0001

Data Index: 1620935 (Python Code)

Max Activating Token Index: 267

Text #10

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9870. Min Act: -0.0001

Data Index: 1532892 (Python Code)

Max Activating Token Index: 495

Text #11

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9724. Min Act: -0.0001

Data Index: 790162 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9962. Min Act: -0.0001

Data Index: 53206 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9923. Min Act: -0.0001

Data Index: 271828 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9619. Min Act: -0.0001

Data Index: 497606 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9450. Min Act: -0.0001

Data Index: 1614827 (Python Code)

Max Activating Token Index: 650

Text #16

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.8229. Min Act: -0.0001

Data Index: 1148994 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9607. Min Act: -0.0001

Data Index: 610030 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9537. Min Act: -0.0001

Data Index: 1260976 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9453. Min Act: -0.0001

Data Index: 993779 (C4 (Web Text))

Max Activating Token Index: 116