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

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

Neuron 675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.9771. Min Act: -0.0000

Data Index: 1313281 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.5334. Min Act: -0.0000

Data Index: 16388 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.1598. Min Act: -0.0000

Data Index: 690840 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1085230 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1248308 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.0143. Min Act: -0.0000

Data Index: 876843 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1052211 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9287. Min Act: -0.0000

Data Index: 479870 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.0311. Min Act: -0.0000

Data Index: 658 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9741. Min Act: -0.0000

Data Index: 704725 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9535. Min Act: -0.0000

Data Index: 505951 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9758. Min Act: -0.0000

Data Index: 933286 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9669. Min Act: -0.0000

Data Index: 719892 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9901. Min Act: -0.0000

Data Index: 481804 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9610. Min Act: -0.0000

Data Index: 530649 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1029575 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1339291 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.8725. Min Act: -0.0000

Data Index: 772530 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1341467 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.9771. Min Range: -1.9771

Max Act: 0.8409. Min Act: -0.0000

Data Index: 383978 (C4 (Web Text))

Max Activating Token Index: 417