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

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

Neuron 905 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3918. Min Act: -0.0001

Data Index: 1226003 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3669. Min Act: -0.0001

Data Index: 334204 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3818. Min Act: -0.0001

Data Index: 525445 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3671. Min Act: -0.0001

Data Index: 392445 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3535. Min Act: -0.0001

Data Index: 47050 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3682. Min Act: -0.0001

Data Index: 784372 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3549. Min Act: -0.0001

Data Index: 736536 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3521. Min Act: -0.0001

Data Index: 876635 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3243. Min Act: -0.0001

Data Index: 217122 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3320. Min Act: -0.0001

Data Index: 766964 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3263. Min Act: -0.0001

Data Index: 827566 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3196. Min Act: -0.0001

Data Index: 348623 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3279. Min Act: -0.0001

Data Index: 1293142 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1268575 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3121. Min Act: -0.0001

Data Index: 812504 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1051570 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1184541 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3021. Min Act: -0.0001

Data Index: 367120 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3006. Min Act: -0.0001

Data Index: 629871 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3060. Min Act: -0.0001

Data Index: 944830 (C4 (Web Text))

Max Activating Token Index: 232