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

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

Neuron 1355 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2841. Min Range: -2.2841

Max Act: 2.2841. Min Act: -0.0000

Data Index: 1066469 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.7130. Min Act: -0.0000

Data Index: 6304 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.6934. Min Act: -0.0000

Data Index: 997773 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.7386. Min Act: -0.0000

Data Index: 633268 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.8089. Min Act: -0.0000

Data Index: 265086 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.7124. Min Act: -0.0000

Data Index: 928595 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.6537. Min Act: -0.0000

Data Index: 123932 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.5897. Min Act: -0.0000

Data Index: 430516 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.4245. Min Act: -0.0000

Data Index: 572760 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.6719. Min Act: -0.0000

Data Index: 117871 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.7186. Min Act: -0.0000

Data Index: 186404 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.5853. Min Act: -0.0000

Data Index: 1157002 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.6959. Min Act: -0.0000

Data Index: 1340266 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.5001. Min Act: -0.0000

Data Index: 654519 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1097602 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.5902. Min Act: -0.0000

Data Index: 264073 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.5416. Min Act: -0.0000

Data Index: 506019 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.4943. Min Act: -0.0000

Data Index: 1256287 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.4866. Min Act: -0.0000

Data Index: 335367 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 2.2841. Min Range: -2.2841

Max Act: 1.5148. Min Act: -0.0000

Data Index: 501929 (C4 (Web Text))

Max Activating Token Index: 644