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

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

Neuron 229 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: 2.3665. Min Range: -2.3665

Max Act: 2.3665. Min Act: -0.0000

Data Index: 1381255 (Python Code)

Max Activating Token Index: 797

Text #1

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.8187. Min Act: -0.0000

Data Index: 1486303 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.8980. Min Act: -0.0000

Data Index: 1597160 (Python Code)

Max Activating Token Index: 611

Text #3

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.8393. Min Act: -0.0001

Data Index: 1540807 (Python Code)

Max Activating Token Index: 658

Text #4

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.8741. Min Act: -0.0000

Data Index: 1606336 (Python Code)

Max Activating Token Index: 1019

Text #5

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.8932. Min Act: -0.0000

Data Index: 1440044 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.8296. Min Act: -0.0001

Data Index: 1372486 (Python Code)

Max Activating Token Index: 178

Text #7

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.8983. Min Act: -0.0000

Data Index: 1571848 (Python Code)

Max Activating Token Index: 277

Text #8

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.6948. Min Act: -0.0001

Data Index: 202775 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.7880. Min Act: -0.0000

Data Index: 1552200 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.7165. Min Act: -0.0001

Data Index: 988913 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.7789. Min Act: -0.0000

Data Index: 1527179 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.7653. Min Act: -0.0000

Data Index: 1480818 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.8069. Min Act: -0.0000

Data Index: 1614911 (Python Code)

Max Activating Token Index: 404

Text #14

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.7713. Min Act: -0.0000

Data Index: 1526465 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.5776. Min Act: -0.0001

Data Index: 997786 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.6455. Min Act: -0.0001

Data Index: 372341 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.5405. Min Act: -0.0000

Data Index: 1581345 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1405591 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 2.3665. Min Range: -2.3665

Max Act: 1.4253. Min Act: -0.0000

Data Index: 86155 (C4 (Web Text))

Max Activating Token Index: 842