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

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

Neuron 5025 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.2832. Min Act: -0.0000

Data Index: 736171 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1551526 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.5766. Min Act: -0.0000

Data Index: 815046 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1392871 (Python Code)

Max Activating Token Index: 962

Text #4

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1638323 (Python Code)

Max Activating Token Index: 276

Text #5

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1453210 (Python Code)

Max Activating Token Index: 1016

Text #6

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1423235 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1397824 (Python Code)

Max Activating Token Index: 417

Text #8

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1370941 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1488796 (Python Code)

Max Activating Token Index: 717

Text #10

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1434688 (Python Code)

Max Activating Token Index: 298

Text #11

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1650114 (Python Code)

Max Activating Token Index: 601

Text #12

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1385043 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1624405 (Python Code)

Max Activating Token Index: 279

Text #14

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4412. Min Act: -0.0000

Data Index: 702942 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1390429 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1627411 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1465031 (Python Code)

Max Activating Token Index: 254

Text #18

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1482524 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1601874 (Python Code)

Max Activating Token Index: 302