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

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

Neuron 578 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: 1.8592. Min Range: -1.8592

Max Act: 1.7970. Min Act: -0.0000

Data Index: 64092 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.8592. Min Act: -0.0000

Data Index: 293141 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1286890 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.7695. Min Act: -0.0000

Data Index: 651838 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.7275. Min Act: -0.0000

Data Index: 299043 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.8183. Min Act: -0.0000

Data Index: 1300863 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.7996. Min Act: -0.0000

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.7158. Min Act: -0.0000

Data Index: 1169895 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.6389. Min Act: -0.0000

Data Index: 673925 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.7203. Min Act: -0.0000

Data Index: 998426 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5379. Min Act: -0.0000

Data Index: 21311 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.7171. Min Act: -0.0000

Data Index: 734704 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5337. Min Act: -0.0000

Data Index: 97587 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.7247. Min Act: -0.0000

Data Index: 315776 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5973. Min Act: -0.0000

Data Index: 421020 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5980. Min Act: -0.0000

Data Index: 1163920 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5613. Min Act: -0.0000

Data Index: 439096 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5312. Min Act: -0.0000

Data Index: 197809 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.4317. Min Act: -0.0000

Data Index: 812979 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.8592. Min Range: -1.8592

Max Act: 1.5129. Min Act: -0.0000

Data Index: 322800 (C4 (Web Text))

Max Activating Token Index: 880