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

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

Neuron 1763 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3951. Min Range: -1.3951

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1186709 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.3951. Min Range: -1.3951

Max Act: 1.3951. Min Act: -0.0000

Data Index: 1250911 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 1.3951. Min Range: -1.3951

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1340832 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 1.3951. Min Range: -1.3951

Max Act: 1.1908. Min Act: -0.0000

Data Index: 728652 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.3951. Min Range: -1.3951

Max Act: 1.0761. Min Act: -0.0000

Data Index: 64908 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.3951. Min Range: -1.3951

Max Act: 1.0605. Min Act: -0.0000

Data Index: 273395 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.9876. Min Act: -0.0000

Data Index: 10267 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.3951. Min Range: -1.3951

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1213084 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.9474. Min Act: -0.0000

Data Index: 198464 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.3951. Min Range: -1.3951

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1161750 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.9928. Min Act: -0.0000

Data Index: 725976 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1016676 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.9247. Min Act: -0.0000

Data Index: 548562 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1137484 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.8520. Min Act: -0.0000

Data Index: 330763 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1278398 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.8727. Min Act: -0.0000

Data Index: 103095 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.8702. Min Act: -0.0000

Data Index: 907020 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.8469. Min Act: -0.0000

Data Index: 580913 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.3951. Min Range: -1.3951

Max Act: 0.8892. Min Act: -0.0000

Data Index: 239782 (C4 (Web Text))

Max Activating Token Index: 821