Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 867 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1655. Min Act: -0.0002

Data Index: 1338338 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1552. Min Act: -0.0002

Data Index: 1428878 (Python Code)

Max Activating Token Index: 415

Text #2

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1528929 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1537. Min Act: -0.0001

Data Index: 663056 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1362. Min Act: -0.0002

Data Index: 1365070 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1466. Min Act: -0.0002

Data Index: 1404458 (Python Code)

Max Activating Token Index: 938

Text #6

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1404. Min Act: -0.0002

Data Index: 1543158 (Python Code)

Max Activating Token Index: 637

Text #7

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1416. Min Act: -0.0002

Data Index: 1441297 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1362. Min Act: -0.0002

Data Index: 930241 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1346. Min Act: -0.0002

Data Index: 576881 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1606480 (Python Code)

Max Activating Token Index: 539

Text #11

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1560158 (Python Code)

Max Activating Token Index: 357

Text #12

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1411986 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1199. Min Act: -0.0002

Data Index: 978326 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1259574 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1301704 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1494172 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1080974 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1635846 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 0.1655. Min Range: -0.1655

Max Act: 0.1300. Min Act: -0.0002

Data Index: 448546 (C4 (Web Text))

Max Activating Token Index: 909