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

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

Neuron 3156 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: 2.1942. Min Range: -2.1942

Max Act: 2.1138. Min Act: 0.0000

Data Index: 533386 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 2.1942. Min Range: -2.1942

Max Act: 2.1942. Min Act: -0.0000

Data Index: 127223 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 2.1942. Min Range: -2.1942

Max Act: 2.0401. Min Act: 0.0001

Data Index: 531152 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 2.1942. Min Range: -2.1942

Max Act: 2.0124. Min Act: -0.0000

Data Index: 891293 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.9953. Min Act: -0.0000

Data Index: 722081 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.9583. Min Act: -0.0000

Data Index: 94903 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.7240. Min Act: -0.0000

Data Index: 132638 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.8112. Min Act: -0.0000

Data Index: 711938 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.7155. Min Act: -0.0000

Data Index: 1132724 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.8330. Min Act: -0.0000

Data Index: 401448 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.8442. Min Act: -0.0000

Data Index: 1040185 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1230111 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.6007. Min Act: -0.0000

Data Index: 956172 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.6953. Min Act: -0.0000

Data Index: 188830 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.5494. Min Act: -0.0000

Data Index: 441736 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.5457. Min Act: -0.0000

Data Index: 812555 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.5412. Min Act: -0.0000

Data Index: 938074 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.6147. Min Act: -0.0000

Data Index: 49349 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.5155. Min Act: -0.0000

Data Index: 1031611 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 2.1942. Min Range: -2.1942

Max Act: 1.5741. Min Act: -0.0000

Data Index: 774699 (C4 (Web Text))

Max Activating Token Index: 164