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

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

Neuron 736 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.3074. Min Act: -0.0000

Data Index: 140106 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2993. Min Act: -0.0000

Data Index: 200981 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2389. Min Act: -0.0000

Data Index: 823883 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2220. Min Act: -0.0000

Data Index: 16304 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2147. Min Act: -0.0000

Data Index: 66386 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1045329 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2140. Min Act: -0.0000

Data Index: 475428 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2045. Min Act: -0.0000

Data Index: 211461 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2032. Min Act: -0.0000

Data Index: 212405 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2101. Min Act: -0.0000

Data Index: 364717 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2010. Min Act: -0.0000

Data Index: 249065 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1974. Min Act: -0.0000

Data Index: 781478 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2016. Min Act: -0.0000

Data Index: 907195 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1946. Min Act: 0.0000

Data Index: 143783 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1876. Min Act: -0.0000

Data Index: 979538 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1244170 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1927. Min Act: -0.0000

Data Index: 858573 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1926. Min Act: -0.0000

Data Index: 77389 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1932. Min Act: -0.0000

Data Index: 810216 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1887. Min Act: 0.0000

Data Index: 600303 (C4 (Web Text))

Max Activating Token Index: 56