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

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

Neuron 2668 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: 0.8636. Min Range: -0.8636

Max Act: 0.8636. Min Act: -0.0001

Data Index: 453146 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.8477. Min Act: -0.0001

Data Index: 1336459 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.8507. Min Act: -0.0001

Data Index: 165982 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.8324. Min Act: -0.0001

Data Index: 1181681 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.8276. Min Act: -0.0001

Data Index: 1268870 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7950. Min Act: -0.0001

Data Index: 660693 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7739. Min Act: -0.0001

Data Index: 583921 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7672. Min Act: -0.0001

Data Index: 187265 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7701. Min Act: -0.0001

Data Index: 1077063 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7845. Min Act: -0.0001

Data Index: 830510 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7541. Min Act: -0.0001

Data Index: 232032 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7479. Min Act: -0.0001

Data Index: 1149275 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7675. Min Act: -0.0001

Data Index: 244449 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7446. Min Act: -0.0001

Data Index: 564038 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1041385 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7517. Min Act: -0.0001

Data Index: 1328504 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7466. Min Act: -0.0001

Data Index: 145642 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7398. Min Act: -0.0001

Data Index: 513528 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1151167 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.8636. Min Range: -0.8636

Max Act: 0.7367. Min Act: -0.0001

Data Index: 126702 (C4 (Web Text))

Max Activating Token Index: 788