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

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

Neuron 5467 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: 0.5055. Min Range: -0.5055

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1246039 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4815. Min Act: -0.0000

Data Index: 915900 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4363. Min Act: -0.0000

Data Index: 523742 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1351019 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4494. Min Act: -0.0000

Data Index: 303760 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4013. Min Act: -0.0000

Data Index: 188836 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4149. Min Act: -0.0000

Data Index: 815656 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3845. Min Act: -0.0000

Data Index: 807090 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1561710 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.4013. Min Act: -0.0000

Data Index: 539436 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1260961 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3686. Min Act: -0.0000

Data Index: 482291 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3892. Min Act: -0.0000

Data Index: 627880 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1474458 (Python Code)

Max Activating Token Index: 235

Text #14

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3682. Min Act: 0.0000

Data Index: 304064 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1421561 (Python Code)

Max Activating Token Index: 896

Text #16

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3674. Min Act: -0.0000

Data Index: 156322 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1417404 (Python Code)

Max Activating Token Index: 252

Text #18

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1475932 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 0.5055. Min Range: -0.5055

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1274016 (C4 (Web Text))

Max Activating Token Index: 393