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

Dataset: The Pile

Neuron 2771 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0000

Data Index: 1639431 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0253. Min Act: -0.0000

Data Index: 1583701 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0238. Min Act: -0.0000

Data Index: 736549 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0243. Min Act: -0.0000

Data Index: 1503698 (The Pile)

Max Activating Token Index: 59

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0245. Min Act: -0.0000

Data Index: 638359 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1411689 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1592271 (The Pile)

Max Activating Token Index: 989

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0235. Min Act: -0.0000

Data Index: 96442 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0237. Min Act: -0.0000

Data Index: 66502 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0232. Min Act: -0.0000

Data Index: 532039 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0230. Min Act: -0.0000

Data Index: 659153 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0229. Min Act: -0.0000

Data Index: 385545 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0224. Min Act: -0.0000

Data Index: 1469567 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0228. Min Act: -0.0001

Data Index: 1930608 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0227. Min Act: -0.0000

Data Index: 559955 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0227. Min Act: -0.0000

Data Index: 1274021 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0227. Min Act: -0.0000

Data Index: 1162988 (The Pile)

Max Activating Token Index: 26

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0218. Min Act: -0.0000

Data Index: 1696776 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0224. Min Act: -0.0000

Data Index: 1583231 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0224. Min Act: -0.0000

Data Index: 1290098 (The Pile)

Max Activating Token Index: 472