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

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

Neuron 3907 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2763. Min Act: -0.0000

Data Index: 814679 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2687. Min Act: -0.0000

Data Index: 461033 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1145088 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1225424 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1191025 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1335824 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1212159 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2116. Min Act: 0.0001

Data Index: 715502 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1342982 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2216. Min Act: 0.0001

Data Index: 698992 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2110. Min Act: -0.0000

Data Index: 458732 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2135. Min Act: -0.0000

Data Index: 313914 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2055. Min Act: -0.0001

Data Index: 914461 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1979. Min Act: 0.0000

Data Index: 1014691 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2040. Min Act: -0.0000

Data Index: 410110 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1325676 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2052. Min Act: -0.0001

Data Index: 979480 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2067. Min Act: -0.0000

Data Index: 22387 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1912. Min Act: -0.0000

Data Index: 224150 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1991. Min Act: -0.0001

Data Index: 575367 (C4 (Web Text))

Max Activating Token Index: 844