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

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

Neuron 5337 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: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0001

Data Index: 845185 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0490. Min Act: -0.0001

Data Index: 443374 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1164714 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0481. Min Act: -0.0001

Data Index: 518640 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0453. Min Act: -0.0001

Data Index: 333883 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1291153 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0450. Min Act: -0.0001

Data Index: 541091 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1348957 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1187416 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0421. Min Act: -0.0001

Data Index: 81248 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0432. Min Act: -0.0001

Data Index: 821490 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0424. Min Act: -0.0001

Data Index: 289509 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0419. Min Act: -0.0001

Data Index: 596965 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0421. Min Act: -0.0001

Data Index: 840618 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0419. Min Act: -0.0001

Data Index: 499715 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0418. Min Act: -0.0001

Data Index: 59427 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0411. Min Act: -0.0001

Data Index: 367996 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0419. Min Act: -0.0001

Data Index: 76200 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0413. Min Act: -0.0001

Data Index: 328675 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1168938 (C4 (Web Text))

Max Activating Token Index: 173