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

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

Neuron 4095 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: 1.1253. Min Range: -1.1253

Max Act: 1.1253. Min Act: -0.0001

Data Index: 211571 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.1253. Min Range: -1.1253

Max Act: 1.0438. Min Act: -0.0001

Data Index: 830099 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.9699. Min Act: -0.0001

Data Index: 383638 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.9716. Min Act: -0.0001

Data Index: 1175253 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.9265. Min Act: -0.0001

Data Index: 310822 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.9854. Min Act: -0.0001

Data Index: 286227 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.1253. Min Range: -1.1253

Max Act: 1.0967. Min Act: -0.0001

Data Index: 1332583 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.9172. Min Act: -0.0001

Data Index: 940423 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1139102 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.8201. Min Act: -0.0001

Data Index: 1093832 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.9617. Min Act: -0.0001

Data Index: 1209154 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.8892. Min Act: -0.0001

Data Index: 937381 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.8077. Min Act: -0.0001

Data Index: 183771 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.9140. Min Act: -0.0001

Data Index: 1065960 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.7347. Min Act: -0.0001

Data Index: 342748 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.8007. Min Act: -0.0001

Data Index: 948224 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.5889. Min Act: -0.0001

Data Index: 76240 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.7802. Min Act: -0.0001

Data Index: 1249086 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.8022. Min Act: -0.0001

Data Index: 735573 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.1253. Min Range: -1.1253

Max Act: 0.7752. Min Act: -0.0001

Data Index: 394879 (C4 (Web Text))

Max Activating Token Index: 388