Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1916900 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1352025 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5842. Min Act: -0.0000

Data Index: 879405 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5297. Min Act: -0.0001

Data Index: 1389468 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5454. Min Act: -0.0000

Data Index: 920880 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1699056 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5200. Min Act: -0.0000

Data Index: 550517 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5291. Min Act: -0.0000

Data Index: 86918 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1907212 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1645059 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1962653 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5399. Min Act: -0.0000

Data Index: 422472 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5400. Min Act: -0.0000

Data Index: 525664 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5211. Min Act: -0.0001

Data Index: 1672661 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4993. Min Act: -0.0000

Data Index: 22299 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5186. Min Act: -0.0001

Data Index: 1634101 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5168. Min Act: -0.0001

Data Index: 529408 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4965. Min Act: -0.0001

Data Index: 1467146 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1635900 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5093. Min Act: -0.0000

Data Index: 851318 (The Pile)

Max Activating Token Index: 783