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

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

Neuron 3557 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4997. Min Range: -1.4997

Max Act: 1.4997. Min Act: -0.0001

Data Index: 1205073 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 1.4997. Min Range: -1.4997

Max Act: 1.3441. Min Act: -0.0002

Data Index: 1058315 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.4997. Min Range: -1.4997

Max Act: 1.3077. Min Act: -0.0001

Data Index: 336595 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 1.4997. Min Range: -1.4997

Max Act: 1.0955. Min Act: -0.0001

Data Index: 106891 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 1.4997. Min Range: -1.4997

Max Act: 1.1330. Min Act: -0.0001

Data Index: 76527 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.8964. Min Act: -0.0001

Data Index: 1294081 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.4997. Min Range: -1.4997

Max Act: 1.0323. Min Act: -0.0001

Data Index: 411056 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.9549. Min Act: -0.0001

Data Index: 176954 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.8776. Min Act: -0.0001

Data Index: 194459 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.9717. Min Act: -0.0002

Data Index: 1183829 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.9352. Min Act: -0.0001

Data Index: 1009888 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 1.4997. Min Range: -1.4997

Max Act: 1.0913. Min Act: -0.0001

Data Index: 1078468 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 1.4997. Min Range: -1.4997

Max Act: 1.0039. Min Act: -0.0001

Data Index: 487591 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.7823. Min Act: -0.0001

Data Index: 810062 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.9774. Min Act: -0.0001

Data Index: 1340076 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.9343. Min Act: -0.0001

Data Index: 420814 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.8180. Min Act: -0.0001

Data Index: 1064738 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.7985. Min Act: -0.0001

Data Index: 760820 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.9451. Min Act: -0.0001

Data Index: 432877 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 1.4997. Min Range: -1.4997

Max Act: 0.8899. Min Act: -0.0001

Data Index: 847148 (C4 (Web Text))

Max Activating Token Index: 960