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

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

Neuron 1768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.4094. Min Act: -0.0000

Data Index: 622632 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.3099. Min Act: -0.0000

Data Index: 66656 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1321517 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.2877. Min Act: -0.0000

Data Index: 495874 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.2123. Min Act: -0.0000

Data Index: 617215 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.2028. Min Act: -0.0000

Data Index: 949197 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1629. Min Act: -0.0000

Data Index: 5834 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1312. Min Act: -0.0000

Data Index: 939207 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1535. Min Act: -0.0000

Data Index: 439908 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.0873. Min Act: -0.0000

Data Index: 739631 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1069. Min Act: -0.0000

Data Index: 361122 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1007. Min Act: -0.0000

Data Index: 404318 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1645. Min Act: -0.0000

Data Index: 507400 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.0869. Min Act: -0.0000

Data Index: 886739 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1179. Min Act: -0.0000

Data Index: 67630 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1279. Min Act: -0.0000

Data Index: 356179 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1193680 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1324. Min Act: -0.0000

Data Index: 306149 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.0924. Min Act: -0.0000

Data Index: 305973 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.0341. Min Act: -0.0000

Data Index: 894191 (C4 (Web Text))

Max Activating Token Index: 446