Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 291 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.5054. Min Act: -0.0005

Data Index: 1321621 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4891. Min Act: -0.0005

Data Index: 1096556 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4792. Min Act: -0.0005

Data Index: 884876 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4283. Min Act: -0.0005

Data Index: 656253 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4552. Min Act: -0.0005

Data Index: 266284 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4219. Min Act: -0.0005

Data Index: 741013 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4199. Min Act: -0.0005

Data Index: 83155 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3911. Min Act: -0.0005

Data Index: 1089203 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4211. Min Act: -0.0005

Data Index: 596718 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4155. Min Act: -0.0005

Data Index: 903713 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3965. Min Act: -0.0005

Data Index: 617193 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3894. Min Act: -0.0005

Data Index: 914898 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3747. Min Act: -0.0005

Data Index: 512446 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4000. Min Act: -0.0005

Data Index: 461261 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3980. Min Act: -0.0005

Data Index: 193142 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3850. Min Act: -0.0005

Data Index: 12696 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3714. Min Act: -0.0005

Data Index: 925298 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3982. Min Act: -0.0005

Data Index: 1328237 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3966. Min Act: -0.0005

Data Index: 958600 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3854. Min Act: -0.0005

Data Index: 93656 (C4 (Web Text))

Max Activating Token Index: 280