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

Dataset: The Pile

Neuron 1866 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.2691. Min Act: -0.0000

Data Index: 1327665 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.2198. Min Act: -0.0000

Data Index: 819663 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.0676. Min Act: -0.0000

Data Index: 933095 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1683330 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1118866 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 1.2691. Min Range: -1.2691

Max Act: 0.9983. Min Act: -0.0000

Data Index: 400399 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1421690 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.2239. Min Act: -0.0000

Data Index: 613382 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 1.2691. Min Range: -1.2691

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1026145 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1105771 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.1226. Min Act: -0.0001

Data Index: 968169 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.1397. Min Act: -0.0000

Data Index: 353273 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 1.2691. Min Range: -1.2691

Max Act: 0.9212. Min Act: -0.0000

Data Index: 445172 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.2264. Min Act: -0.0000

Data Index: 922617 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 1.2691. Min Range: -1.2691

Max Act: 0.9259. Min Act: -0.0000

Data Index: 591236 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1942796 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 1.2691. Min Range: -1.2691

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1689899 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 1.2691. Min Range: -1.2691

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1043846 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 1.2691. Min Range: -1.2691

Max Act: 0.8187. Min Act: -0.0000

Data Index: 144277 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 1.2691. Min Range: -1.2691

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1474043 (The Pile)

Max Activating Token Index: 261