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

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

Neuron 4955 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: 1.2842. Min Range: -1.2842

Max Act: 1.2842. Min Act: -0.0001

Data Index: 409059 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.9537. Min Act: -0.0001

Data Index: 1581947 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1104569 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.8863. Min Act: -0.0001

Data Index: 419310 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.9175. Min Act: -0.0000

Data Index: 675464 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.8702. Min Act: -0.0001

Data Index: 597279 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.8128. Min Act: -0.0001

Data Index: 1562920 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7714. Min Act: -0.0001

Data Index: 549734 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.8901. Min Act: -0.0001

Data Index: 1394809 (Python Code)

Max Activating Token Index: 597

Text #9

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7520. Min Act: -0.0001

Data Index: 34081 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7201. Min Act: -0.0001

Data Index: 1581994 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.8079. Min Act: -0.0000

Data Index: 35696 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7584. Min Act: -0.0001

Data Index: 1217551 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7780. Min Act: -0.0001

Data Index: 1618548 (Python Code)

Max Activating Token Index: 265

Text #14

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.8117. Min Act: -0.0001

Data Index: 898693 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7517. Min Act: -0.0001

Data Index: 1264897 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7045. Min Act: -0.0001

Data Index: 1134456 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7013. Min Act: -0.0001

Data Index: 536133 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.6918. Min Act: -0.0001

Data Index: 424535 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.2842. Min Range: -1.2842

Max Act: 0.7175. Min Act: -0.0001

Data Index: 501971 (C4 (Web Text))

Max Activating Token Index: 2