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

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

Neuron 751 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: 0.9408. Min Range: -0.9408

Max Act: 0.9408. Min Act: -0.0002

Data Index: 1026396 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8838. Min Act: -0.0002

Data Index: 296848 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7464. Min Act: -0.0002

Data Index: 767917 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7231. Min Act: -0.0002

Data Index: 761571 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7102. Min Act: -0.0002

Data Index: 901277 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6958. Min Act: -0.0003

Data Index: 256515 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6827. Min Act: -0.0002

Data Index: 1339655 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6844. Min Act: -0.0002

Data Index: 1119601 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6674. Min Act: -0.0002

Data Index: 1044319 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6820. Min Act: -0.0002

Data Index: 155093 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6678. Min Act: -0.0002

Data Index: 574934 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6779. Min Act: -0.0002

Data Index: 753841 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6526. Min Act: -0.0002

Data Index: 423886 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6398. Min Act: -0.0002

Data Index: 252617 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6261. Min Act: -0.0003

Data Index: 460809 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6289. Min Act: -0.0002

Data Index: 697936 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6344. Min Act: -0.0002

Data Index: 1206741 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6225. Min Act: -0.0002

Data Index: 940527 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6168. Min Act: -0.0002

Data Index: 419313 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6180. Min Act: -0.0002

Data Index: 943553 (C4 (Web Text))

Max Activating Token Index: 1005