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

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

Neuron 1627 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1469. Min Range: -2.1469

Max Act: 2.0672. Min Act: -0.0000

Data Index: 1547720 (Python Code)

Max Activating Token Index: 725

Text #1

Max Range: 2.1469. Min Range: -2.1469

Max Act: 2.1469. Min Act: -0.0000

Data Index: 1526809 (Python Code)

Max Activating Token Index: 831

Text #2

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.8549. Min Act: -0.0000

Data Index: 1470065 (Python Code)

Max Activating Token Index: 447

Text #3

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.7441. Min Act: -0.0000

Data Index: 1654946 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.7951. Min Act: -0.0000

Data Index: 1489510 (Python Code)

Max Activating Token Index: 139

Text #5

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.6794. Min Act: -0.0000

Data Index: 838192 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.6264. Min Act: -0.0000

Data Index: 1429905 (Python Code)

Max Activating Token Index: 968

Text #7

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.5488. Min Act: -0.0000

Data Index: 1414656 (Python Code)

Max Activating Token Index: 750

Text #8

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1024464 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.5738. Min Act: -0.0000

Data Index: 1511212 (Python Code)

Max Activating Token Index: 1017

Text #10

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.7181. Min Act: -0.0000

Data Index: 1636279 (Python Code)

Max Activating Token Index: 447

Text #11

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.6482. Min Act: -0.0000

Data Index: 1655062 (Python Code)

Max Activating Token Index: 936

Text #12

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1512680 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.6395. Min Act: -0.0000

Data Index: 557457 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.7797. Min Act: -0.0000

Data Index: 1445930 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.5988. Min Act: -0.0000

Data Index: 833488 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1433220 (Python Code)

Max Activating Token Index: 931

Text #17

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.5241. Min Act: -0.0000

Data Index: 1655385 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1572482 (Python Code)

Max Activating Token Index: 900

Text #19

Max Range: 2.1469. Min Range: -2.1469

Max Act: 1.7216. Min Act: -0.0000

Data Index: 1571270 (Python Code)

Max Activating Token Index: 996