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

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

Neuron 76 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1220211 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1467762 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1484748 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1446893 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1133910 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1360368 (Python Code)

Max Activating Token Index: 420

Text #6

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1532765 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2998. Min Act: -0.0000

Data Index: 199018 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1383352 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1641677 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1587351 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2777. Min Act: -0.0000

Data Index: 320216 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3020. Min Act: -0.0000

Data Index: 313070 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2678. Min Act: -0.0000

Data Index: 334194 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1519051 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1625988 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1339603 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1037177 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2287. Min Act: -0.0000

Data Index: 124548 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1412026 (Python Code)

Max Activating Token Index: 668