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

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

Neuron 752 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: 2.1989. Min Range: -2.1989

Max Act: 2.1270. Min Act: -0.0000

Data Index: 1124695 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 2.1989. Min Range: -2.1989

Max Act: 2.1989. Min Act: -0.0000

Data Index: 1341265 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 2.1989. Min Range: -2.1989

Max Act: 2.0203. Min Act: -0.0000

Data Index: 536024 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.6456. Min Act: -0.0000

Data Index: 915473 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.6269. Min Act: -0.0000

Data Index: 17477 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.6285. Min Act: -0.0000

Data Index: 959402 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.7049. Min Act: -0.0000

Data Index: 790507 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.6393. Min Act: -0.0000

Data Index: 232727 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.6268. Min Act: -0.0000

Data Index: 677172 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.5959. Min Act: -0.0000

Data Index: 906058 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.5887. Min Act: -0.0000

Data Index: 845331 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.4957. Min Act: -0.0000

Data Index: 722785 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.4918. Min Act: -0.0000

Data Index: 1327021 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.5797. Min Act: -0.0000

Data Index: 874203 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1009601 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.4771. Min Act: -0.0000

Data Index: 222595 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.4679. Min Act: -0.0000

Data Index: 256407 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.5871. Min Act: -0.0000

Data Index: 851204 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.5054. Min Act: -0.0000

Data Index: 771890 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 2.1989. Min Range: -2.1989

Max Act: 1.4973. Min Act: -0.0000

Data Index: 198098 (C4 (Web Text))

Max Activating Token Index: 462