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

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

Neuron 4770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4937. Min Act: -0.0000

Data Index: 314143 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2892. Min Act: -0.0000

Data Index: 453307 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1047673 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1023876 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2003. Min Act: -0.0000

Data Index: 328347 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2134. Min Act: -0.0000

Data Index: 1042664 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1858. Min Act: -0.0000

Data Index: 103793 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1992. Min Act: -0.0000

Data Index: 437338 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1277600 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1311144 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2149. Min Act: -0.0000

Data Index: 909479 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1938. Min Act: -0.0000

Data Index: 6870 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1879. Min Act: -0.0000

Data Index: 786974 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1677. Min Act: -0.0000

Data Index: 741469 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1580. Min Act: -0.0000

Data Index: 639423 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1914. Min Act: -0.0000

Data Index: 830408 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1773. Min Act: -0.0000

Data Index: 894218 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1621. Min Act: -0.0000

Data Index: 452482 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1247159 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.1951. Min Act: -0.0000

Data Index: 680106 (C4 (Web Text))

Max Activating Token Index: 268