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

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

Neuron 2707 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: 0.4930. Min Range: -0.4930

Max Act: 0.4930. Min Act: -0.0001

Data Index: 415961 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1167858 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4286. Min Act: -0.0000

Data Index: 81466 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4583. Min Act: -0.0000

Data Index: 228192 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4392. Min Act: -0.0001

Data Index: 270648 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4292. Min Act: -0.0001

Data Index: 1162143 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4147. Min Act: -0.0000

Data Index: 522018 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1156680 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3982. Min Act: -0.0001

Data Index: 1176521 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4194. Min Act: -0.0000

Data Index: 772536 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3924. Min Act: -0.0001

Data Index: 1246488 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3971. Min Act: -0.0000

Data Index: 193000 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3947. Min Act: -0.0001

Data Index: 854492 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1081392 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4155. Min Act: -0.0000

Data Index: 11307 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.4026. Min Act: -0.0000

Data Index: 656708 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3717. Min Act: -0.0001

Data Index: 496985 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3830. Min Act: -0.0000

Data Index: 281218 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3549. Min Act: -0.0001

Data Index: 526963 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.4930. Min Range: -0.4930

Max Act: 0.3644. Min Act: -0.0000

Data Index: 64601 (C4 (Web Text))

Max Activating Token Index: 156