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

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

Neuron 4532 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: 0.3323. Min Range: -0.3323

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1201453 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3187. Min Act: -0.0000

Data Index: 734212 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3299. Min Act: -0.0000

Data Index: 559311 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3193. Min Act: -0.0000

Data Index: 792203 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3242. Min Act: -0.0000

Data Index: 696536 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1236139 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3097. Min Act: -0.0000

Data Index: 119332 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2905. Min Act: -0.0000

Data Index: 795198 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1009744 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2493. Min Act: -0.0000

Data Index: 499328 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2564. Min Act: -0.0000

Data Index: 35363 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2403. Min Act: -0.0000

Data Index: 296043 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2233. Min Act: -0.0000

Data Index: 942664 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2351. Min Act: -0.0000

Data Index: 528984 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1298093 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2184. Min Act: -0.0000

Data Index: 829807 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2084. Min Act: -0.0000

Data Index: 375780 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2057. Min Act: -0.0000

Data Index: 506754 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2040. Min Act: -0.0000

Data Index: 789127 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2017. Min Act: -0.0000

Data Index: 594443 (C4 (Web Text))

Max Activating Token Index: 47