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

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

Neuron 5597 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8340. Min Range: -2.8340

Max Act: 2.8340. Min Act: -0.0000

Data Index: 1646767 (Python Code)

Max Activating Token Index: 636

Text #1

Max Range: 2.8340. Min Range: -2.8340

Max Act: 2.3487. Min Act: -0.0000

Data Index: 1457522 (Python Code)

Max Activating Token Index: 515

Text #2

Max Range: 2.8340. Min Range: -2.8340

Max Act: 2.3496. Min Act: -0.0000

Data Index: 1509228 (Python Code)

Max Activating Token Index: 594

Text #3

Max Range: 2.8340. Min Range: -2.8340

Max Act: 2.1372. Min Act: -0.0000

Data Index: 1591492 (Python Code)

Max Activating Token Index: 552

Text #4

Max Range: 2.8340. Min Range: -2.8340

Max Act: 2.1260. Min Act: -0.0000

Data Index: 1502248 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 2.8340. Min Range: -2.8340

Max Act: 2.0991. Min Act: -0.0000

Data Index: 1372136 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.9928. Min Act: 0.0000

Data Index: 1523327 (Python Code)

Max Activating Token Index: 961

Text #7

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.9495. Min Act: -0.0000

Data Index: 1635241 (Python Code)

Max Activating Token Index: 820

Text #8

Max Range: 2.8340. Min Range: -2.8340

Max Act: 2.0280. Min Act: -0.0000

Data Index: 1548875 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.7766. Min Act: 0.0001

Data Index: 1434243 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.7553. Min Act: -0.0000

Data Index: 1623278 (Python Code)

Max Activating Token Index: 202

Text #11

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.8499. Min Act: -0.0000

Data Index: 1460284 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.8522. Min Act: -0.0000

Data Index: 1512031 (Python Code)

Max Activating Token Index: 577

Text #13

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.7116. Min Act: 0.0000

Data Index: 1465224 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.8037. Min Act: -0.0000

Data Index: 1549750 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.9159. Min Act: -0.0000

Data Index: 1414633 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.9207. Min Act: 0.0000

Data Index: 1615650 (Python Code)

Max Activating Token Index: 336

Text #17

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.7312. Min Act: 0.0000

Data Index: 1433222 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.8345. Min Act: -0.0000

Data Index: 1393463 (Python Code)

Max Activating Token Index: 291

Text #19

Max Range: 2.8340. Min Range: -2.8340

Max Act: 1.8068. Min Act: -0.0000

Data Index: 1492488 (Python Code)

Max Activating Token Index: 564