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

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

Neuron 4708 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: 1.6621. Min Range: -1.6621

Max Act: 1.6621. Min Act: -0.0000

Data Index: 284870 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.5106. Min Act: -0.0000

Data Index: 385688 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.3749. Min Act: -0.0000

Data Index: 233363 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.2183. Min Act: -0.0000

Data Index: 1191659 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.3468. Min Act: -0.0000

Data Index: 357414 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1051584 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.3232. Min Act: -0.0000

Data Index: 951778 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1249385 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.2525. Min Act: -0.0000

Data Index: 8988 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1595. Min Act: -0.0000

Data Index: 695439 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1034225 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.2167. Min Act: -0.0000

Data Index: 437877 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.2176. Min Act: -0.0000

Data Index: 441973 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.2203. Min Act: -0.0000

Data Index: 382229 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1180934 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1483. Min Act: -0.0000

Data Index: 664992 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1431. Min Act: -0.0000

Data Index: 439611 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1822. Min Act: -0.0000

Data Index: 165070 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1666. Min Act: -0.0000

Data Index: 302956 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.6621. Min Range: -1.6621

Max Act: 1.1528. Min Act: -0.0000

Data Index: 24342 (C4 (Web Text))

Max Activating Token Index: 100