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

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

Neuron 3170 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7870. Min Act: -0.0001

Data Index: 988186 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1272199 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7126. Min Act: -0.0001

Data Index: 1255310 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6423. Min Act: -0.0001

Data Index: 684223 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7258. Min Act: -0.0001

Data Index: 510399 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6655. Min Act: -0.0001

Data Index: 684383 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6604. Min Act: -0.0001

Data Index: 720129 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6463. Min Act: -0.0001

Data Index: 901919 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6133. Min Act: -0.0001

Data Index: 747809 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6097. Min Act: -0.0001

Data Index: 514555 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6028. Min Act: -0.0001

Data Index: 1160267 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6184. Min Act: -0.0001

Data Index: 512839 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6088. Min Act: -0.0001

Data Index: 574483 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5880. Min Act: -0.0001

Data Index: 277304 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5824. Min Act: -0.0001

Data Index: 140772 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5838. Min Act: -0.0001

Data Index: 125635 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5552. Min Act: -0.0001

Data Index: 1136284 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5214. Min Act: -0.0001

Data Index: 1096292 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5542. Min Act: -0.0001

Data Index: 1146203 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5501. Min Act: -0.0001

Data Index: 147095 (C4 (Web Text))

Max Activating Token Index: 195