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

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

Neuron 2215 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1205747 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4401. Min Act: -0.0000

Data Index: 752729 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1247779 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4339. Min Act: -0.0000

Data Index: 554839 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4432. Min Act: -0.0000

Data Index: 2867 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1546698 (Python Code)

Max Activating Token Index: 893

Text #6

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4288. Min Act: -0.0000

Data Index: 739710 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1461459 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4176. Min Act: -0.0000

Data Index: 303000 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4017. Min Act: -0.0000

Data Index: 953009 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4019. Min Act: -0.0000

Data Index: 526715 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3951. Min Act: -0.0000

Data Index: 554733 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1591077 (Python Code)

Max Activating Token Index: 376

Text #13

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3914. Min Act: -0.0000

Data Index: 791375 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3919. Min Act: -0.0000

Data Index: 34519 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1095870 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1394277 (Python Code)

Max Activating Token Index: 813

Text #17

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4006. Min Act: -0.0000

Data Index: 222808 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1053776 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.5293. Min Range: -0.5293

Max Act: 0.3953. Min Act: -0.0000

Data Index: 147355 (C4 (Web Text))

Max Activating Token Index: 22