Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2598 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.6770. Min Act: -0.0000

Data Index: 302189 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.6664. Min Act: -0.0000

Data Index: 528976 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.6249. Min Act: -0.0000

Data Index: 666828 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.5955. Min Act: -0.0000

Data Index: 972872 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.4052. Min Act: -0.0000

Data Index: 514736 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.4731. Min Act: -0.0000

Data Index: 226596 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.3038. Min Act: -0.0000

Data Index: 159876 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.1678. Min Act: -0.0000

Data Index: 1110196 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.2523. Min Act: -0.0000

Data Index: 612348 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.0312. Min Act: -0.0000

Data Index: 294096 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.0925. Min Act: -0.0000

Data Index: 490543 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 2.6770. Min Range: -2.6770

Max Act: 1.8356. Min Act: -0.0000

Data Index: 1213663 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.0124. Min Act: -0.0000

Data Index: 867457 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.0104. Min Act: -0.0000

Data Index: 1128827 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 2.6770. Min Range: -2.6770

Max Act: 2.0028. Min Act: -0.0000

Data Index: 521227 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 2.6770. Min Range: -2.6770

Max Act: 1.9584. Min Act: -0.0000

Data Index: 1187536 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 2.6770. Min Range: -2.6770

Max Act: 1.9356. Min Act: -0.0000

Data Index: 438812 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 2.6770. Min Range: -2.6770

Max Act: 1.9133. Min Act: -0.0000

Data Index: 1056201 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 2.6770. Min Range: -2.6770

Max Act: 1.7529. Min Act: -0.0000

Data Index: 456184 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 2.6770. Min Range: -2.6770

Max Act: 1.8849. Min Act: -0.0000

Data Index: 1028668 (C4 (Web Text))

Max Activating Token Index: 713