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

Dataset: The Pile

Neuron 4239 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: 0.8875. Min Range: -0.8875

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1033519 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1903390 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1545161 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1961804 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1754438 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8725. Min Act: -0.0000

Data Index: 273257 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1157648 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8193. Min Act: -0.0000

Data Index: 546953 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1593397 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8233. Min Act: -0.0000

Data Index: 30733 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1875345 (The Pile)

Max Activating Token Index: 269

Text #11

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6591. Min Act: -0.0000

Data Index: 506163 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1425236 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1280421 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1920550 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1770984 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1156040 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7199. Min Act: -0.0000

Data Index: 987304 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1176684 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7531. Min Act: -0.0000

Data Index: 280395 (The Pile)

Max Activating Token Index: 236