Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1615 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2680. Min Act: -0.0001

Data Index: 173438 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2353. Min Act: -0.0000

Data Index: 503588 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2168. Min Act: -0.0000

Data Index: 24979 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1056881 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2178. Min Act: -0.0000

Data Index: 350558 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2080. Min Act: -0.0000

Data Index: 861112 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1960. Min Act: -0.0000

Data Index: 770352 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1936. Min Act: -0.0001

Data Index: 264718 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1903. Min Act: -0.0000

Data Index: 43138 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1891. Min Act: -0.0000

Data Index: 500567 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1752. Min Act: -0.0000

Data Index: 881434 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1937. Min Act: -0.0000

Data Index: 246150 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1906. Min Act: -0.0001

Data Index: 240368 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1840. Min Act: -0.0001

Data Index: 710262 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1283245 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1799. Min Act: -0.0000

Data Index: 117471 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1728. Min Act: -0.0000

Data Index: 985906 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1717. Min Act: -0.0001

Data Index: 1344902 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1787. Min Act: -0.0000

Data Index: 206046 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1697. Min Act: -0.0000

Data Index: 439068 (C4 (Web Text))

Max Activating Token Index: 74