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

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

Neuron 4516 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: 2.3349. Min Range: -2.3349

Max Act: 2.3349. Min Act: -0.0002

Data Index: 343775 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 2.3349. Min Range: -2.3349

Max Act: 2.0119. Min Act: -0.0002

Data Index: 153203 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.9738. Min Act: -0.0002

Data Index: 594104 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.8892. Min Act: -0.0002

Data Index: 507483 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.8395. Min Act: -0.0003

Data Index: 1288510 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.8849. Min Act: -0.0002

Data Index: 889378 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.8731. Min Act: -0.0003

Data Index: 856599 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.7744. Min Act: -0.0002

Data Index: 981898 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.7947. Min Act: -0.0002

Data Index: 450742 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.7482. Min Act: -0.0002

Data Index: 414356 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.7810. Min Act: -0.0002

Data Index: 191406 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.7162. Min Act: -0.0002

Data Index: 1193033 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.7030. Min Act: -0.0002

Data Index: 1231086 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.7160. Min Act: -0.0002

Data Index: 893846 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.6288. Min Act: -0.0002

Data Index: 877628 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.6317. Min Act: -0.0002

Data Index: 1102480 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.6497. Min Act: -0.0002

Data Index: 1017234 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.6381. Min Act: -0.0002

Data Index: 796544 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.5851. Min Act: -0.0002

Data Index: 850301 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 2.3349. Min Range: -2.3349

Max Act: 1.5791. Min Act: -0.0003

Data Index: 991174 (C4 (Web Text))

Max Activating Token Index: 331