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

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

Neuron 4814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3284. Min Act: -0.0000

Data Index: 384898 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1216239 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3065. Min Act: -0.0000

Data Index: 711283 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3181. Min Act: -0.0000

Data Index: 189626 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3142. Min Act: -0.0000

Data Index: 935010 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2401. Min Act: -0.0000

Data Index: 592766 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2768. Min Act: -0.0000

Data Index: 250862 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1487697 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2632. Min Act: -0.0000

Data Index: 20277 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1624913 (Python Code)

Max Activating Token Index: 646

Text #10

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1561962 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1529716 (Python Code)

Max Activating Token Index: 901

Text #12

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1112120 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1641103 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1542288 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2235. Min Act: -0.0000

Data Index: 40636 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2474. Min Act: -0.0000

Data Index: 521321 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2381. Min Act: -0.0000

Data Index: 609450 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2304. Min Act: -0.0000

Data Index: 493224 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1559252 (Python Code)

Max Activating Token Index: 805