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

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

Neuron 587 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2783. Min Act: -0.0001

Data Index: 70041 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1559331 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2293. Min Act: -0.0000

Data Index: 224509 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1649419 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1520548 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1266978 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2125. Min Act: -0.0000

Data Index: 97833 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1044428 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2098. Min Act: -0.0000

Data Index: 416745 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2164. Min Act: -0.0000

Data Index: 725865 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1254208 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2193. Min Act: -0.0000

Data Index: 27984 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1638708 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2156. Min Act: -0.0000

Data Index: 334400 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1321003 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2074. Min Act: -0.0000

Data Index: 345456 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2119. Min Act: -0.0000

Data Index: 879152 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.2046. Min Act: -0.0000

Data Index: 199010 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1377404 (Python Code)

Max Activating Token Index: 285

Text #19

Max Range: 0.2783. Min Range: -0.2783

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1631625 (Python Code)

Max Activating Token Index: 984