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

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

Neuron 1153 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0300. Min Range: -3.0300

Max Act: 3.0300. Min Act: -0.0000

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.7319. Min Act: -0.0000

Data Index: 149593 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.6608. Min Act: -0.0001

Data Index: 983472 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.5668. Min Act: -0.0001

Data Index: 319025 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.5266. Min Act: -0.0001

Data Index: 451624 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.6884. Min Act: -0.0001

Data Index: 1222579 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.5189. Min Act: -0.0000

Data Index: 1135477 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.2080. Min Act: -0.0000

Data Index: 730285 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.3676. Min Act: -0.0001

Data Index: 369960 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.2465. Min Act: -0.0001

Data Index: 1125834 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.3899. Min Act: -0.0001

Data Index: 944321 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.1853. Min Act: -0.0001

Data Index: 1072850 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 3.0300. Min Range: -3.0300

Max Act: 1.9924. Min Act: -0.0001

Data Index: 1277406 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.2150. Min Act: -0.0001

Data Index: 948327 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.1970. Min Act: -0.0001

Data Index: 1177757 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.1822. Min Act: -0.0000

Data Index: 291233 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.0123. Min Act: -0.0001

Data Index: 782945 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 3.0300. Min Range: -3.0300

Max Act: 1.8906. Min Act: -0.0001

Data Index: 460297 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.0130. Min Act: -0.0000

Data Index: 116017 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 3.0300. Min Range: -3.0300

Max Act: 2.0019. Min Act: -0.0000

Data Index: 1267761 (C4 (Web Text))

Max Activating Token Index: 485