Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 889 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1163. Min Range: -1.1163

Max Act: 1.1163. Min Act: -0.0001

Data Index: 963686 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.1163. Min Range: -1.1163

Max Act: 1.1010. Min Act: 0.0001

Data Index: 1395886 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 1.1163. Min Range: -1.1163

Max Act: 1.0700. Min Act: -0.0000

Data Index: 985187 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9609. Min Act: -0.0001

Data Index: 1528286 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9698. Min Act: -0.0001

Data Index: 1620757 (Python Code)

Max Activating Token Index: 547

Text #5

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9137. Min Act: -0.0001

Data Index: 280594 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1353708 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1530163 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8785. Min Act: 0.0000

Data Index: 1404324 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8277. Min Act: 0.0000

Data Index: 1628813 (Python Code)

Max Activating Token Index: 638

Text #10

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8445. Min Act: -0.0001

Data Index: 1414438 (Python Code)

Max Activating Token Index: 682

Text #11

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8687. Min Act: -0.0001

Data Index: 1639194 (Python Code)

Max Activating Token Index: 890

Text #12

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1617785 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1530928 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8291. Min Act: 0.0002

Data Index: 1381962 (Python Code)

Max Activating Token Index: 538

Text #15

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8297. Min Act: 0.0000

Data Index: 1530417 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1536603 (Python Code)

Max Activating Token Index: 187

Text #17

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1395559 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.8357. Min Act: -0.0001

Data Index: 1216262 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.1163. Min Range: -1.1163

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1613521 (Python Code)

Max Activating Token Index: 123