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

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

Neuron 22 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1302286 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.7134. Min Act: -0.0000

Data Index: 302809 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.8138. Min Act: -0.0001

Data Index: 1322079 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6520. Min Act: -0.0000

Data Index: 679182 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.7095. Min Act: -0.0000

Data Index: 892890 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.7231. Min Act: -0.0001

Data Index: 521889 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6935. Min Act: -0.0001

Data Index: 377488 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6572. Min Act: -0.0000

Data Index: 794369 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6757. Min Act: -0.0001

Data Index: 1001218 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1257297 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6416. Min Act: -0.0001

Data Index: 304713 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6349. Min Act: -0.0000

Data Index: 507698 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6284. Min Act: -0.0000

Data Index: 172872 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1341608 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1147205 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6271. Min Act: -0.0000

Data Index: 345510 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.5996. Min Act: -0.0000

Data Index: 735948 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6172. Min Act: 0.0000

Data Index: 203939 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.6345. Min Act: -0.0001

Data Index: 1209145 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.8138. Min Range: -0.8138

Max Act: 0.5934. Min Act: -0.0001

Data Index: 523701 (C4 (Web Text))

Max Activating Token Index: 36