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

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

Neuron 5609 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.9820. Min Act: -0.0001

Data Index: 71585 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1551485 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1388063 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1413036 (Python Code)

Max Activating Token Index: 169

Text #4

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1503030 (Python Code)

Max Activating Token Index: 523

Text #5

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1602539 (Python Code)

Max Activating Token Index: 555

Text #6

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1394412 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1471577 (Python Code)

Max Activating Token Index: 920

Text #8

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.8435. Min Act: -0.0001

Data Index: 1526290 (Python Code)

Max Activating Token Index: 58

Text #9

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1641133 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1555746 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1454138 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1364760 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1503084 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1595615 (Python Code)

Max Activating Token Index: 415

Text #15

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1612530 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1541242 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1540305 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1615944 (Python Code)

Max Activating Token Index: 423

Text #19

Max Range: 0.9820. Min Range: -0.9820

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1628689 (Python Code)

Max Activating Token Index: 68