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

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

Neuron 3220 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2704. Min Act: -0.0000

Data Index: 914846 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1238223 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2529. Min Act: -0.0000

Data Index: 818762 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2259. Min Act: -0.0000

Data Index: 282005 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1118936 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2209. Min Act: -0.0000

Data Index: 513453 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2162. Min Act: -0.0000

Data Index: 81122 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2047. Min Act: -0.0000

Data Index: 242695 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2094. Min Act: -0.0000

Data Index: 277077 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1075821 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2310. Min Act: -0.0000

Data Index: 524193 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2141. Min Act: -0.0000

Data Index: 704418 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1305191 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2180. Min Act: -0.0000

Data Index: 739738 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1868. Min Act: -0.0000

Data Index: 743494 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1950. Min Act: -0.0000

Data Index: 747223 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1179399 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2181. Min Act: -0.0000

Data Index: 810326 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1946. Min Act: -0.0000

Data Index: 910915 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2024. Min Act: -0.0000

Data Index: 148500 (C4 (Web Text))

Max Activating Token Index: 898