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

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

Neuron 5248 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: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0000

Data Index: 375104 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0391. Min Act: -0.0000

Data Index: 487786 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1123378 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0370. Min Act: -0.0000

Data Index: 1249395 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0390. Min Act: -0.0000

Data Index: 420517 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0343. Min Act: -0.0000

Data Index: 660907 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1013777 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1528914 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1234233 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1232020 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0340. Min Act: -0.0000

Data Index: 957231 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0335. Min Act: -0.0000

Data Index: 186169 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0346. Min Act: -0.0000

Data Index: 1405735 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0329. Min Act: -0.0000

Data Index: 372216 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1190229 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0314. Min Act: -0.0000

Data Index: 318562 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0340. Min Act: -0.0000

Data Index: 728557 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0323. Min Act: -0.0000

Data Index: 670836 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0325. Min Act: -0.0000

Data Index: 591479 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0318. Min Act: -0.0000

Data Index: 321994 (C4 (Web Text))

Max Activating Token Index: 728