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

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

Neuron 381 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: 0.9406. Min Range: -0.9406

Max Act: 0.9406. Min Act: -0.0002

Data Index: 1158255 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.8659. Min Act: -0.0002

Data Index: 951255 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.8173. Min Act: -0.0002

Data Index: 454562 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.8043. Min Act: -0.0002

Data Index: 740611 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7957. Min Act: -0.0002

Data Index: 1000963 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.8035. Min Act: -0.0002

Data Index: 853904 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7747. Min Act: -0.0002

Data Index: 881662 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7681. Min Act: -0.0002

Data Index: 219921 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7735. Min Act: -0.0002

Data Index: 735212 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7680. Min Act: -0.0002

Data Index: 434257 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7420. Min Act: -0.0002

Data Index: 163281 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7471. Min Act: -0.0002

Data Index: 580516 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7336. Min Act: -0.0002

Data Index: 169959 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7303. Min Act: -0.0002

Data Index: 912550 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7258. Min Act: -0.0002

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7222. Min Act: -0.0002

Data Index: 705858 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7028. Min Act: -0.0002

Data Index: 630097 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7188. Min Act: -0.0002

Data Index: 1197014 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7125. Min Act: -0.0002

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.9406. Min Range: -0.9406

Max Act: 0.7152. Min Act: -0.0002

Data Index: 855659 (C4 (Web Text))

Max Activating Token Index: 571