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

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

Neuron 4361 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4684. Min Act: -0.0001

Data Index: 399145 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4474. Min Act: -0.0001

Data Index: 703653 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4476. Min Act: -0.0001

Data Index: 535200 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4295. Min Act: -0.0001

Data Index: 1242162 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4464. Min Act: -0.0001

Data Index: 644866 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4491. Min Act: -0.0001

Data Index: 988883 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3791. Min Act: -0.0001

Data Index: 97344 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4299. Min Act: -0.0001

Data Index: 240248 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4381. Min Act: -0.0001

Data Index: 729347 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4239. Min Act: -0.0001

Data Index: 1191213 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1194908 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3964. Min Act: -0.0001

Data Index: 1338642 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4206. Min Act: -0.0001

Data Index: 859273 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4207. Min Act: -0.0001

Data Index: 1321513 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4026. Min Act: -0.0001

Data Index: 282428 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4344. Min Act: -0.0001

Data Index: 112588 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4100. Min Act: -0.0001

Data Index: 976595 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4170. Min Act: -0.0001

Data Index: 500833 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3909. Min Act: -0.0001

Data Index: 612507 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1165697 (C4 (Web Text))

Max Activating Token Index: 520