Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2155 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1561329 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6245. Min Act: -0.0000

Data Index: 820614 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6108. Min Act: -0.0000

Data Index: 310863 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5750. Min Act: -0.0000

Data Index: 957876 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5704. Min Act: -0.0000

Data Index: 313821 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1262056 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1272022 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5266. Min Act: -0.0000

Data Index: 379978 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1197530 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5048. Min Act: -0.0000

Data Index: 346397 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1872848 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1354602 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1565743 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5012. Min Act: -0.0000

Data Index: 575190 (The Pile)

Max Activating Token Index: 646

Text #14

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1797198 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1746632 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1193386 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5063. Min Act: -0.0000

Data Index: 499445 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5213. Min Act: -0.0000

Data Index: 601682 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1262590 (The Pile)

Max Activating Token Index: 547