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

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

Neuron 5038 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: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1340510 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0334. Min Act: -0.0002

Data Index: 922192 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0331. Min Act: -0.0002

Data Index: 155217 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0331. Min Act: -0.0002

Data Index: 428378 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1494553 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1043374 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0310. Min Act: -0.0002

Data Index: 292471 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0299. Min Act: -0.0002

Data Index: 96324 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0295. Min Act: -0.0002

Data Index: 630360 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0298. Min Act: -0.0002

Data Index: 499761 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1012537 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0290. Min Act: -0.0002

Data Index: 512064 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0289. Min Act: -0.0002

Data Index: 968835 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0292. Min Act: -0.0002

Data Index: 364086 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1290645 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0288. Min Act: -0.0002

Data Index: 906287 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0293. Min Act: -0.0002

Data Index: 819686 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0286. Min Act: -0.0002

Data Index: 796387 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1552 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1158442 (C4 (Web Text))

Max Activating Token Index: 653