Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1845 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2925. Min Act: -0.0001

Data Index: 1223635 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2762. Min Act: -0.0002

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1344041 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2497. Min Act: -0.0001

Data Index: 203096 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2194. Min Act: -0.0002

Data Index: 1096979 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2076. Min Act: -0.0001

Data Index: 668670 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2026. Min Act: -0.0001

Data Index: 881985 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2074. Min Act: -0.0002

Data Index: 172692 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2052. Min Act: -0.0002

Data Index: 144204 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2034. Min Act: -0.0002

Data Index: 1258332 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2082. Min Act: -0.0001

Data Index: 1108879 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1996. Min Act: -0.0001

Data Index: 226337 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1314445 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1861. Min Act: -0.0002

Data Index: 337617 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1692. Min Act: -0.0001

Data Index: 540759 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1896. Min Act: -0.0002

Data Index: 1239402 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1813. Min Act: -0.0001

Data Index: 922679 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1986. Min Act: -0.0002

Data Index: 1272636 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1773. Min Act: -0.0001

Data Index: 1099920 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1835. Min Act: -0.0001

Data Index: 754314 (C4 (Web Text))

Max Activating Token Index: 272