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

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

Neuron 5303 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: 1.9431. Min Range: -1.9431

Max Act: 1.9431. Min Act: -0.0000

Data Index: 1530958 (Python Code)

Max Activating Token Index: 602

Text #1

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.9271. Min Act: -0.0000

Data Index: 1628362 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.7144. Min Act: -0.0000

Data Index: 1644052 (Python Code)

Max Activating Token Index: 620

Text #3

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.7349. Min Act: -0.0000

Data Index: 1477938 (Python Code)

Max Activating Token Index: 915

Text #4

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.7179. Min Act: -0.0000

Data Index: 1413704 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.6366. Min Act: -0.0001

Data Index: 1578062 (Python Code)

Max Activating Token Index: 205

Text #6

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.6378. Min Act: -0.0000

Data Index: 1542486 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.7229. Min Act: -0.0000

Data Index: 1387538 (Python Code)

Max Activating Token Index: 94

Text #8

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.6428. Min Act: -0.0000

Data Index: 1373297 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.5408. Min Act: -0.0000

Data Index: 1577630 (Python Code)

Max Activating Token Index: 623

Text #10

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1459976 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1473267 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1643209 (Python Code)

Max Activating Token Index: 827

Text #13

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.6927. Min Act: -0.0001

Data Index: 1477471 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.5317. Min Act: -0.0001

Data Index: 1487280 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.5570. Min Act: -0.0001

Data Index: 1604588 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.6352. Min Act: -0.0000

Data Index: 1648155 (Python Code)

Max Activating Token Index: 1007

Text #17

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1369006 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1524752 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 1.9431. Min Range: -1.9431

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1541336 (Python Code)

Max Activating Token Index: 3