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

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

Neuron 936 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: 0.3035. Min Range: -0.3035

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1290887 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2983. Min Act: -0.0000

Data Index: 796837 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2472. Min Act: -0.0000

Data Index: 431385 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1226635 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2594. Min Act: -0.0000

Data Index: 791964 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1054984 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2639. Min Act: -0.0000

Data Index: 517197 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2753. Min Act: -0.0000

Data Index: 22861 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2225. Min Act: -0.0000

Data Index: 686423 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2027. Min Act: -0.0000

Data Index: 417008 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2047. Min Act: -0.0000

Data Index: 39067 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2170. Min Act: -0.0000

Data Index: 348927 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2273. Min Act: -0.0000

Data Index: 526965 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2233. Min Act: -0.0000

Data Index: 68095 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2167. Min Act: -0.0000

Data Index: 113387 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1637935 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1963. Min Act: -0.0000

Data Index: 697991 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1753. Min Act: -0.0000

Data Index: 265014 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1818. Min Act: -0.0000

Data Index: 899389 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2089. Min Act: -0.0000

Data Index: 544187 (C4 (Web Text))

Max Activating Token Index: 397