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

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

Neuron 446 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0359. Min Range: -2.0359

Max Act: 2.0359. Min Act: -0.0000

Data Index: 1310383 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.9064. Min Act: -0.0000

Data Index: 1305033 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1655092 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.5909. Min Act: -0.0000

Data Index: 424069 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.4878. Min Act: -0.0000

Data Index: 1603986 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.6445. Min Act: -0.0000

Data Index: 1515636 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1491320 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1525820 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.5804. Min Act: -0.0000

Data Index: 1555087 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.5417. Min Act: -0.0000

Data Index: 1575579 (Python Code)

Max Activating Token Index: 377

Text #10

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.4861. Min Act: -0.0000

Data Index: 416044 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.6410. Min Act: -0.0000

Data Index: 380516 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.5105. Min Act: -0.0000

Data Index: 1632390 (Python Code)

Max Activating Token Index: 379

Text #13

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1467884 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.3769. Min Act: -0.0000

Data Index: 1649756 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.4071. Min Act: -0.0000

Data Index: 654968 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.2388. Min Act: -0.0000

Data Index: 28334 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1398335 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.3640. Min Act: -0.0000

Data Index: 320525 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 2.0359. Min Range: -2.0359

Max Act: 1.3249. Min Act: -0.0000

Data Index: 328082 (C4 (Web Text))

Max Activating Token Index: 360