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

Dataset: The Pile

Neuron 2850 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.6006. Min Act: -0.0000

Data Index: 1538082 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.5666. Min Act: -0.0000

Data Index: 911443 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.6233. Min Act: -0.0000

Data Index: 2399 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1154102 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1673938 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1283565 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2952. Min Act: -0.0000

Data Index: 783194 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1938750 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2103. Min Act: -0.0000

Data Index: 796848 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3777. Min Act: -0.0000

Data Index: 285330 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1971430 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.1949. Min Act: -0.0000

Data Index: 473109 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2239. Min Act: -0.0000

Data Index: 1736949 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2169. Min Act: -0.0000

Data Index: 195929 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2858. Min Act: -0.0000

Data Index: 558453 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1115194 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1105905 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1010993 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1146896 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1106653 (The Pile)

Max Activating Token Index: 486