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

Dataset: The Pile

Neuron 1405 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1146061 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1323719 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6099. Min Act: -0.0000

Data Index: 96137 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1141753 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1347591 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6412. Min Act: -0.0000

Data Index: 184161 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6305. Min Act: -0.0000

Data Index: 530817 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6158. Min Act: -0.0000

Data Index: 500493 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6273. Min Act: -0.0000

Data Index: 736626 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1936665 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6256. Min Act: -0.0000

Data Index: 560206 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1187427 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6022. Min Act: -0.0000

Data Index: 223820 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1161786 (The Pile)

Max Activating Token Index: 420

Text #14

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5903. Min Act: -0.0000

Data Index: 647453 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6147. Min Act: -0.0000

Data Index: 315398 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6158. Min Act: -0.0000

Data Index: 43647 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6133. Min Act: -0.0000

Data Index: 272210 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6078. Min Act: -0.0000

Data Index: 260681 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1334334 (The Pile)

Max Activating Token Index: 529