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

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

Neuron 6111 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.5438. Min Act: -0.0000

Data Index: 607877 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.0373. Min Act: -0.0000

Data Index: 883819 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8629. Min Act: -0.0000

Data Index: 803473 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8473. Min Act: -0.0000

Data Index: 326901 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8143. Min Act: -0.0000

Data Index: 639808 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8628. Min Act: -0.0000

Data Index: 636441 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8351. Min Act: -0.0000

Data Index: 378702 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8120. Min Act: -0.0000

Data Index: 571492 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8587. Min Act: -0.0000

Data Index: 221850 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8323. Min Act: -0.0000

Data Index: 201070 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.8084. Min Act: -0.0000

Data Index: 803519 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7961. Min Act: -0.0000

Data Index: 933904 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7907. Min Act: -0.0000

Data Index: 763686 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1072645 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7618. Min Act: -0.0000

Data Index: 389561 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1031770 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7405. Min Act: -0.0000

Data Index: 505838 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7955. Min Act: -0.0000

Data Index: 976254 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7209. Min Act: -0.0000

Data Index: 890663 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.5438. Min Range: -1.5438

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1329592 (C4 (Web Text))

Max Activating Token Index: 385