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

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

Neuron 1561 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: 0.2969. Min Range: -0.2969

Max Act: 0.2969. Min Act: 0.0003

Data Index: 451679 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2630. Min Act: -0.0000

Data Index: 710832 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1220867 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2328. Min Act: 0.0003

Data Index: 1143346 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1217873 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2188. Min Act: 0.0001

Data Index: 150692 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2189. Min Act: 0.0000

Data Index: 1172300 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2285. Min Act: 0.0003

Data Index: 723880 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2151. Min Act: -0.0000

Data Index: 959002 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1193496 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1922. Min Act: -0.0000

Data Index: 851064 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1970. Min Act: 0.0000

Data Index: 139075 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1160762 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1911. Min Act: 0.0000

Data Index: 1080209 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1905. Min Act: -0.0000

Data Index: 409246 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2034. Min Act: -0.0000

Data Index: 362674 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1262181 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1247281 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1217642 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1943. Min Act: 0.0001

Data Index: 576919 (C4 (Web Text))

Max Activating Token Index: 137