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

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

Neuron 4344 in Layer 0

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: 0.4843. Min Range: -0.4843

Max Act: 0.4843. Min Act: -0.0001

Data Index: 1319263 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4760. Min Act: -0.0001

Data Index: 755017 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4821. Min Act: -0.0001

Data Index: 739677 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4717. Min Act: -0.0001

Data Index: 1242649 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4658. Min Act: -0.0001

Data Index: 552132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4538. Min Act: -0.0001

Data Index: 602631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4522. Min Act: -0.0001

Data Index: 1173498 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4545. Min Act: -0.0001

Data Index: 308372 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4591. Min Act: -0.0001

Data Index: 1316985 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4495. Min Act: -0.0001

Data Index: 893973 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4510. Min Act: -0.0001

Data Index: 1284030 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4475. Min Act: -0.0001

Data Index: 959110 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4507. Min Act: -0.0001

Data Index: 1282137 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4426. Min Act: -0.0001

Data Index: 536303 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4395. Min Act: -0.0001

Data Index: 1241773 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4394. Min Act: -0.0001

Data Index: 649618 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4363. Min Act: -0.0001

Data Index: 432208 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4400. Min Act: -0.0001

Data Index: 109295 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4451. Min Act: -0.0001

Data Index: 908617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.4843. Min Range: -0.4843

Max Act: 0.4354. Min Act: -0.0001

Data Index: 584533 (C4 (Web Text))

Max Activating Token Index: 397