Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 470 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.7974. Min Act: -0.0000

Data Index: 477228 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.7147. Min Act: -0.0000

Data Index: 453549 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1011614 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.6570. Min Act: -0.0000

Data Index: 51920 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1328080 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.6092. Min Act: -0.0000

Data Index: 203906 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.6035. Min Act: -0.0000

Data Index: 794150 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5741. Min Act: -0.0000

Data Index: 697871 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5423. Min Act: -0.0000

Data Index: 615594 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5574. Min Act: -0.0000

Data Index: 127782 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5691. Min Act: -0.0000

Data Index: 681393 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5480. Min Act: -0.0000

Data Index: 809694 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5431. Min Act: -0.0000

Data Index: 537808 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5233. Min Act: -0.0000

Data Index: 823489 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5051. Min Act: -0.0000

Data Index: 198402 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1043709 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.4972. Min Act: -0.0000

Data Index: 603241 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1266908 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.4916. Min Act: -0.0001

Data Index: 732380 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.7974. Min Range: -0.7974

Max Act: 0.5046. Min Act: -0.0000

Data Index: 589416 (C4 (Web Text))

Max Activating Token Index: 602