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

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

Neuron 1839 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: 2.4996. Min Range: -2.4996

Max Act: 2.4996. Min Act: -0.0000

Data Index: 122518 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 2.4996. Min Range: -2.4996

Max Act: 2.0757. Min Act: -0.0000

Data Index: 825300 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 2.4996. Min Range: -2.4996

Max Act: 2.3013. Min Act: -0.0000

Data Index: 1029198 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 2.4996. Min Range: -2.4996

Max Act: 2.1543. Min Act: -0.0000

Data Index: 1253210 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.9889. Min Act: -0.0000

Data Index: 893927 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.9661. Min Act: -0.0000

Data Index: 892548 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.9671. Min Act: -0.0000

Data Index: 367556 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.9316. Min Act: -0.0000

Data Index: 688797 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 2.4996. Min Range: -2.4996

Max Act: 2.0212. Min Act: -0.0000

Data Index: 1154719 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.9500. Min Act: -0.0000

Data Index: 882167 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 2.4996. Min Range: -2.4996

Max Act: 2.0305. Min Act: -0.0000

Data Index: 345077 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.8241. Min Act: -0.0000

Data Index: 32766 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.9453. Min Act: -0.0000

Data Index: 299250 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.7022. Min Act: -0.0000

Data Index: 879343 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.8101. Min Act: -0.0000

Data Index: 1243404 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.7706. Min Act: -0.0000

Data Index: 976255 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1207951 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.8540. Min Act: -0.0000

Data Index: 460428 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.7411. Min Act: -0.0000

Data Index: 374032 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.6230. Min Act: -0.0000

Data Index: 581763 (C4 (Web Text))

Max Activating Token Index: 649