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

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

Neuron 1490 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: 0.7738. Min Range: -0.7738

Max Act: 0.7738. Min Act: -0.0000

Data Index: 120203 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1255941 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.6315. Min Act: -0.0000

Data Index: 751546 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1282842 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7141. Min Act: -0.0000

Data Index: 429586 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5820. Min Act: -0.0000

Data Index: 274337 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1195563 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5737. Min Act: -0.0000

Data Index: 445653 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5919. Min Act: -0.0000

Data Index: 633253 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1343033 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1225326 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5763. Min Act: -0.0000

Data Index: 203555 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5743. Min Act: -0.0000

Data Index: 282728 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5485. Min Act: -0.0000

Data Index: 928208 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5267. Min Act: -0.0000

Data Index: 338415 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1482083 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1311558 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1137386 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1304710 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5205. Min Act: -0.0000

Data Index: 552332 (C4 (Web Text))

Max Activating Token Index: 848