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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 148 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.8771. Min Act: -0.0000

Data Index: 615800 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.8782. Min Act: -0.0000

Data Index: 287790 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.8381. Min Act: -0.0000

Data Index: 985110 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.7298. Min Act: 0.0000

Data Index: 97536 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6726. Min Act: -0.0000

Data Index: 713819 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1078226 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5654. Min Act: -0.0000

Data Index: 717170 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5829. Min Act: -0.0000

Data Index: 307607 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1128501 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5377. Min Act: 0.0000

Data Index: 183050 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5515. Min Act: -0.0000

Data Index: 145941 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1129804 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5279. Min Act: -0.0000

Data Index: 757389 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5278. Min Act: -0.0000

Data Index: 270628 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1227384 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1069250 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.4986. Min Act: -0.0000

Data Index: 49980 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.4994. Min Act: 0.0000

Data Index: 1148805 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.4900. Min Act: 0.0000

Data Index: 685950 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1084563 (C4 (Web Text))

Max Activating Token Index: 190