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

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

Neuron 1118 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.9072. Min Act: -0.0002

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8580. Min Act: -0.0002

Data Index: 452449 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8485. Min Act: -0.0002

Data Index: 908572 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8589. Min Act: -0.0002

Data Index: 747881 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8031. Min Act: -0.0002

Data Index: 614689 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8182. Min Act: -0.0002

Data Index: 424552 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7946. Min Act: -0.0002

Data Index: 1150606 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7821. Min Act: -0.0002

Data Index: 336220 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7848. Min Act: -0.0002

Data Index: 1213586 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8102. Min Act: -0.0002

Data Index: 765397 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8031. Min Act: -0.0002

Data Index: 144117 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7467. Min Act: -0.0002

Data Index: 683481 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7874. Min Act: -0.0002

Data Index: 97618 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8342. Min Act: -0.0002

Data Index: 691800 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7943. Min Act: -0.0002

Data Index: 416050 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7290. Min Act: -0.0002

Data Index: 668974 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7357. Min Act: -0.0002

Data Index: 1115422 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7534. Min Act: -0.0002

Data Index: 791996 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.8077. Min Act: -0.0002

Data Index: 1320142 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 1.9072. Min Range: -1.9072

Max Act: 1.7508. Min Act: -0.0002

Data Index: 701998 (C4 (Web Text))

Max Activating Token Index: 666