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

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

Neuron 4865 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: 0.0598. Min Range: -0.0598

Max Act: 0.0598. Min Act: -0.0001

Data Index: 575930 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1227536 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0532. Min Act: -0.0001

Data Index: 815174 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0539. Min Act: -0.0001

Data Index: 326015 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1211917 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0517. Min Act: -0.0001

Data Index: 915943 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0509. Min Act: -0.0001

Data Index: 961222 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0520. Min Act: -0.0001

Data Index: 133460 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0500. Min Act: -0.0001

Data Index: 563471 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0500. Min Act: -0.0001

Data Index: 908106 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0488. Min Act: -0.0001

Data Index: 468644 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0493. Min Act: -0.0001

Data Index: 126671 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0500. Min Act: -0.0001

Data Index: 819030 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0497. Min Act: -0.0001

Data Index: 944391 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0483. Min Act: -0.0001

Data Index: 808879 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0486. Min Act: -0.0001

Data Index: 418694 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1279701 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0482. Min Act: -0.0001

Data Index: 720508 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0487. Min Act: -0.0001

Data Index: 938769 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1155702 (C4 (Web Text))

Max Activating Token Index: 27