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

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

Neuron 3646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0014. Min Range: -1.0014

Max Act: 1.0014. Min Act: -0.0000

Data Index: 555482 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9597. Min Act: -0.0000

Data Index: 382575 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1269242 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1263198 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9474. Min Act: -0.0000

Data Index: 22249 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1162687 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1244944 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9198. Min Act: -0.0000

Data Index: 217296 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7346. Min Act: -0.0000

Data Index: 831506 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9161. Min Act: -0.0000

Data Index: 227299 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1161162 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8440. Min Act: -0.0000

Data Index: 996765 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1343227 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7716. Min Act: -0.0000

Data Index: 686607 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8433. Min Act: -0.0000

Data Index: 763499 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1112738 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.7620. Min Act: -0.0000

Data Index: 415943 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.9059. Min Act: -0.0000

Data Index: 788968 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1234085 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.0014. Min Range: -1.0014

Max Act: 0.8108. Min Act: -0.0000

Data Index: 201221 (C4 (Web Text))

Max Activating Token Index: 444