Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4979 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6443. Min Act: -0.0002

Data Index: 1570765 (Python Code)

Max Activating Token Index: 631

Text #1

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6331. Min Act: -0.0002

Data Index: 1459508 (Python Code)

Max Activating Token Index: 237

Text #2

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6383. Min Act: -0.0002

Data Index: 1649798 (Python Code)

Max Activating Token Index: 237

Text #3

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6371. Min Act: -0.0002

Data Index: 1629439 (Python Code)

Max Activating Token Index: 948

Text #4

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6299. Min Act: -0.0002

Data Index: 1568143 (Python Code)

Max Activating Token Index: 410

Text #5

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6111. Min Act: -0.0002

Data Index: 1382991 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6128. Min Act: -0.0002

Data Index: 1395343 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6087. Min Act: -0.0002

Data Index: 1450003 (Python Code)

Max Activating Token Index: 441

Text #8

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6044. Min Act: -0.0002

Data Index: 1653091 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5952. Min Act: -0.0002

Data Index: 1474836 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5811. Min Act: -0.0002

Data Index: 1617608 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5830. Min Act: -0.0002

Data Index: 1583162 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5766. Min Act: -0.0002

Data Index: 1433542 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5824. Min Act: -0.0002

Data Index: 1488626 (Python Code)

Max Activating Token Index: 837

Text #14

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5863. Min Act: -0.0002

Data Index: 1378451 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5820. Min Act: -0.0002

Data Index: 1385267 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5857. Min Act: -0.0002

Data Index: 1590314 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5896. Min Act: -0.0002

Data Index: 1456662 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5891. Min Act: -0.0002

Data Index: 1596572 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5727. Min Act: -0.0002

Data Index: 1624924 (Python Code)

Max Activating Token Index: 386