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

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

Neuron 4731 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.5004. Min Act: -0.0000

Data Index: 473360 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.4536. Min Act: -0.0000

Data Index: 1386278 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.5968. Min Act: -0.0000

Data Index: 1374841 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1047827 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.3301. Min Act: -0.0000

Data Index: 1348857 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1554233 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1251936 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1505514 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.2922. Min Act: -0.0000

Data Index: 734312 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.0961. Min Act: -0.0000

Data Index: 678598 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.2567. Min Act: -0.0000

Data Index: 59612 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1336806 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.2194. Min Act: -0.0000

Data Index: 239689 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.1378. Min Act: -0.0000

Data Index: 410555 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1136456 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1290255 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.0825. Min Act: -0.0000

Data Index: 664353 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1489445 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1055482 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.5968. Min Range: -1.5968

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1027698 (C4 (Web Text))

Max Activating Token Index: 604