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

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

Neuron 3229 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: 0.2680. Min Range: -0.2680

Max Act: 0.2680. Min Act: -0.0000

Data Index: 61552 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2322. Min Act: -0.0001

Data Index: 1308394 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2151. Min Act: -0.0000

Data Index: 547487 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1229854 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2124. Min Act: -0.0001

Data Index: 496445 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2054. Min Act: -0.0001

Data Index: 162267 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1350625 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2098. Min Act: -0.0001

Data Index: 64574 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1027702 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1321543 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2072. Min Act: -0.0001

Data Index: 115796 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2052. Min Act: -0.0000

Data Index: 606315 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2052. Min Act: -0.0000

Data Index: 70662 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2048. Min Act: -0.0001

Data Index: 198114 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1073471 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1970. Min Act: -0.0000

Data Index: 52950 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1252736 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1025496 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2038. Min Act: -0.0001

Data Index: 20645 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2014. Min Act: -0.0000

Data Index: 389299 (C4 (Web Text))

Max Activating Token Index: 17