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

Dataset: The Pile

Neuron 2117 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1995146 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2678. Min Act: -0.0000

Data Index: 755824 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2593. Min Act: -0.0000

Data Index: 449412 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1900559 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2381. Min Act: -0.0000

Data Index: 713323 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1368176 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1397160 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1322653 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2013. Min Act: -0.0000

Data Index: 900290 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2193. Min Act: -0.0000

Data Index: 891250 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2192. Min Act: -0.0000

Data Index: 697246 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2185. Min Act: -0.0000

Data Index: 557977 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1052104 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1827. Min Act: -0.0000

Data Index: 263572 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2113. Min Act: -0.0000

Data Index: 433860 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1981. Min Act: -0.0000

Data Index: 946759 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2210. Min Act: -0.0000

Data Index: 98205 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2104. Min Act: -0.0000

Data Index: 2130 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2104. Min Act: -0.0000

Data Index: 769974 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1176408 (The Pile)

Max Activating Token Index: 59