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

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

Neuron 3676 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1128496 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4945. Min Act: -0.0000

Data Index: 266163 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4875. Min Act: -0.0001

Data Index: 332049 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4475. Min Act: -0.0001

Data Index: 118073 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4622. Min Act: -0.0001

Data Index: 1245376 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4502. Min Act: -0.0000

Data Index: 974670 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4298. Min Act: -0.0001

Data Index: 1253513 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4449. Min Act: -0.0001

Data Index: 941879 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4301. Min Act: -0.0000

Data Index: 969191 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4102. Min Act: -0.0001

Data Index: 998844 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4255. Min Act: -0.0000

Data Index: 555303 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4223. Min Act: -0.0000

Data Index: 341537 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4157. Min Act: -0.0000

Data Index: 928946 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4157. Min Act: -0.0000

Data Index: 123977 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3970. Min Act: -0.0001

Data Index: 948095 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4089. Min Act: -0.0001

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4066. Min Act: -0.0001

Data Index: 344200 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.3915. Min Act: -0.0001

Data Index: 37658 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1003651 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.5098. Min Range: -0.5098

Max Act: 0.4157. Min Act: -0.0000

Data Index: 911341 (C4 (Web Text))

Max Activating Token Index: 199