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

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

Neuron 1707 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0602. Min Act: -0.0000

Data Index: 883493 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0000

Data Index: 813743 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1480678 (Python Code)

Max Activating Token Index: 241

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1346597 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0514. Min Act: -0.0000

Data Index: 211926 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1579253 (Python Code)

Max Activating Token Index: 352

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1634954 (Python Code)

Max Activating Token Index: 860

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0462. Min Act: -0.0000

Data Index: 679373 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1627898 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0462. Min Act: -0.0000

Data Index: 786321 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1522004 (Python Code)

Max Activating Token Index: 609

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0443. Min Act: -0.0000

Data Index: 835163 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0429. Min Act: -0.0000

Data Index: 1469276 (Python Code)

Max Activating Token Index: 929

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0446. Min Act: -0.0000

Data Index: 317719 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0467. Min Act: -0.0000

Data Index: 617817 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1296411 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0418. Min Act: -0.0000

Data Index: 663077 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0464. Min Act: -0.0000

Data Index: 554733 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0433. Min Act: -0.0000

Data Index: 1161473 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1225199 (C4 (Web Text))

Max Activating Token Index: 197