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

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

Neuron 2797 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1015711 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2100. Min Act: 0.0001

Data Index: 1115493 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2153. Min Act: -0.0000

Data Index: 62585 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2090. Min Act: -0.0000

Data Index: 746507 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2001. Min Act: -0.0000

Data Index: 153312 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2056. Min Act: -0.0000

Data Index: 802354 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1979. Min Act: -0.0000

Data Index: 864521 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1024802 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1275003 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2030. Min Act: -0.0001

Data Index: 964931 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2056. Min Act: -0.0000

Data Index: 307168 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.2050. Min Act: -0.0001

Data Index: 508707 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1964. Min Act: 0.0002

Data Index: 170342 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1932. Min Act: -0.0000

Data Index: 974527 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1914. Min Act: 0.0001

Data Index: 1257912 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1052453 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1843. Min Act: -0.0001

Data Index: 950489 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1818. Min Act: 0.0001

Data Index: 1175116 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1870. Min Act: -0.0000

Data Index: 466485 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.3085. Min Range: -0.3085

Max Act: 0.1875. Min Act: -0.0000

Data Index: 986420 (C4 (Web Text))

Max Activating Token Index: 967