Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1819 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8917. Min Act: -0.0000

Data Index: 634765 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9472. Min Act: -0.0000

Data Index: 255195 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8945. Min Act: -0.0000

Data Index: 525066 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7687. Min Act: -0.0000

Data Index: 238187 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8146. Min Act: -0.0000

Data Index: 578332 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7405. Min Act: -0.0000

Data Index: 291023 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1478665 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1030201 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1574505 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.5167. Min Act: -0.0000

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1048509 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1159355 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4645. Min Act: -0.0000

Data Index: 520756 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1474193 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4798. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1617968 (Python Code)

Max Activating Token Index: 523

Text #16

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4645. Min Act: -0.0000

Data Index: 845201 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1390855 (Python Code)

Max Activating Token Index: 425

Text #18

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4448. Min Act: -0.0000

Data Index: 660997 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1194618 (C4 (Web Text))

Max Activating Token Index: 210