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

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

Neuron 1406 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.7454. Min Act: -0.0000

Data Index: 1378056 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.7299. Min Act: -0.0000

Data Index: 1425903 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.5914. Min Act: -0.0000

Data Index: 1420630 (Python Code)

Max Activating Token Index: 566

Text #3

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.6129. Min Act: -0.0000

Data Index: 1551254 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.2620. Min Act: -0.0000

Data Index: 1451482 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.5950. Min Act: -0.0001

Data Index: 1451899 (Python Code)

Max Activating Token Index: 515

Text #6

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.6885. Min Act: -0.0000

Data Index: 1570688 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.4937. Min Act: -0.0000

Data Index: 1648188 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.4897. Min Act: -0.0000

Data Index: 1614176 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.3637. Min Act: -0.0000

Data Index: 1652762 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.3302. Min Act: -0.0001

Data Index: 1654832 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.2270. Min Act: -0.0000

Data Index: 1617813 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.4408. Min Act: -0.0000

Data Index: 1465488 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.4299. Min Act: -0.0000

Data Index: 1393125 (Python Code)

Max Activating Token Index: 232

Text #14

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.4265. Min Act: -0.0000

Data Index: 1403062 (Python Code)

Max Activating Token Index: 444

Text #15

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.5547. Min Act: -0.0000

Data Index: 1445385 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.5169. Min Act: -0.0000

Data Index: 1594607 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.2217. Min Act: -0.0000

Data Index: 1652540 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.1095. Min Act: -0.0000

Data Index: 1632454 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 2.7454. Min Range: -2.7454

Max Act: 2.4140. Min Act: -0.0001

Data Index: 1432746 (Python Code)

Max Activating Token Index: 294