Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4478 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8989. Min Range: -2.8989

Max Act: 2.8803. Min Act: -0.0000

Data Index: 463863 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 2.8989. Min Range: -2.8989

Max Act: 2.8989. Min Act: -0.0000

Data Index: 54338 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 2.8989. Min Range: -2.8989

Max Act: 2.8624. Min Act: -0.0000

Data Index: 1261041 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 2.8989. Min Range: -2.8989

Max Act: 2.6825. Min Act: -0.0000

Data Index: 831901 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 2.8989. Min Range: -2.8989

Max Act: 2.2184. Min Act: -0.0000

Data Index: 1330817 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.7439. Min Act: -0.0000

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.7532. Min Act: -0.0000

Data Index: 196675 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.6091. Min Act: -0.0000

Data Index: 59963 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.5627. Min Act: -0.0000

Data Index: 1316407 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.5830. Min Act: -0.0000

Data Index: 649992 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.6405. Min Act: -0.0000

Data Index: 174217 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.4442. Min Act: -0.0000

Data Index: 292722 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.4991. Min Act: -0.0000

Data Index: 91855 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.4540. Min Act: -0.0000

Data Index: 622195 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.4936. Min Act: -0.0000

Data Index: 490683 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.3128. Min Act: -0.0000

Data Index: 1129062 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.4607. Min Act: -0.0000

Data Index: 471437 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.4745. Min Act: -0.0000

Data Index: 507148 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.4467. Min Act: -0.0000

Data Index: 69205 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 2.8989. Min Range: -2.8989

Max Act: 1.5080. Min Act: -0.0000

Data Index: 575426 (C4 (Web Text))

Max Activating Token Index: 1011