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

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

Neuron 3641 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: 2.1070. Min Range: -2.1070

Max Act: 2.1070. Min Act: -0.0000

Data Index: 791473 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7180. Min Act: -0.0000

Data Index: 1118351 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.6983. Min Act: -0.0000

Data Index: 331331 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7763. Min Act: -0.0000

Data Index: 264871 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7238. Min Act: -0.0000

Data Index: 495686 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.8349. Min Act: -0.0000

Data Index: 802364 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7120. Min Act: -0.0000

Data Index: 946093 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.8999. Min Act: -0.0000

Data Index: 91990 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.6462. Min Act: -0.0000

Data Index: 921478 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.5833. Min Act: -0.0000

Data Index: 417647 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.6246. Min Act: -0.0000

Data Index: 274357 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.4961. Min Act: 0.0000

Data Index: 1165814 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.5629. Min Act: -0.0000

Data Index: 154802 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7800. Min Act: -0.0000

Data Index: 1279461 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.6859. Min Act: -0.0000

Data Index: 32887 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1129814 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.8195. Min Act: -0.0000

Data Index: 1254305 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.5599. Min Act: -0.0000

Data Index: 71754 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.5235. Min Act: -0.0000

Data Index: 336232 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7169. Min Act: -0.0000

Data Index: 336567 (C4 (Web Text))

Max Activating Token Index: 881