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

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

Neuron 5507 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.6129. Min Act: -0.0000

Data Index: 1392522 (Python Code)

Max Activating Token Index: 702

Text #1

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.2721. Min Act: -0.0000

Data Index: 1645341 (Python Code)

Max Activating Token Index: 365

Text #2

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.8683. Min Act: -0.0000

Data Index: 1368852 (Python Code)

Max Activating Token Index: 435

Text #3

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.8359. Min Act: -0.0000

Data Index: 1385550 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 3.6129. Min Range: -3.6129

Max Act: 3.1170. Min Act: -0.0000

Data Index: 1484216 (Python Code)

Max Activating Token Index: 971

Text #5

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.6986. Min Act: -0.0000

Data Index: 1533506 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.7048. Min Act: -0.0000

Data Index: 1573120 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.8242. Min Act: 0.0002

Data Index: 1599387 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.5431. Min Act: -0.0000

Data Index: 1497401 (Python Code)

Max Activating Token Index: 997

Text #9

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.4243. Min Act: -0.0000

Data Index: 1370014 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.2698. Min Act: -0.0000

Data Index: 1585768 (Python Code)

Max Activating Token Index: 939

Text #11

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.4676. Min Act: -0.0000

Data Index: 1510348 (Python Code)

Max Activating Token Index: 821

Text #12

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.4960. Min Act: 0.0000

Data Index: 1615429 (Python Code)

Max Activating Token Index: 484

Text #13

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.4730. Min Act: -0.0000

Data Index: 1554458 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.6510. Min Act: -0.0000

Data Index: 1363796 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.5561. Min Act: 0.0001

Data Index: 1642841 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.2999. Min Act: -0.0000

Data Index: 1655887 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.2485. Min Act: -0.0000

Data Index: 1448841 (Python Code)

Max Activating Token Index: 84

Text #18

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.4507. Min Act: -0.0000

Data Index: 1615954 (Python Code)

Max Activating Token Index: 916

Text #19

Max Range: 3.6129. Min Range: -3.6129

Max Act: 2.3156. Min Act: -0.0000

Data Index: 1555290 (Python Code)

Max Activating Token Index: 253