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

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

Neuron 192 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: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1241784 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1655. Min Act: -0.0002

Data Index: 300624 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1731. Min Act: -0.0001

Data Index: 826030 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1461. Min Act: -0.0002

Data Index: 906285 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1188892 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1443. Min Act: -0.0001

Data Index: 203924 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1198. Min Act: -0.0002

Data Index: 98345 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1300. Min Act: -0.0002

Data Index: 7727 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1276. Min Act: -0.0001

Data Index: 834835 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1349834 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1228. Min Act: -0.0002

Data Index: 735465 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1175. Min Act: -0.0002

Data Index: 682183 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1154. Min Act: -0.0002

Data Index: 671064 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1275. Min Act: -0.0001

Data Index: 602392 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1228951 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1105. Min Act: -0.0001

Data Index: 963763 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1129. Min Act: -0.0001

Data Index: 998393 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1007. Min Act: -0.0002

Data Index: 442406 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1116. Min Act: -0.0002

Data Index: 515278 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1073. Min Act: -0.0002

Data Index: 257945 (C4 (Web Text))

Max Activating Token Index: 827