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

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

Neuron 2007 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.7221. Min Act: -0.0000

Data Index: 1644801 (Python Code)

Max Activating Token Index: 403

Text #1

Max Range: 3.0541. Min Range: -3.0541

Max Act: 3.0541. Min Act: -0.0000

Data Index: 1534022 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.7967. Min Act: -0.0000

Data Index: 1628167 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.5968. Min Act: -0.0000

Data Index: 1441940 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.6700. Min Act: -0.0000

Data Index: 1527346 (Python Code)

Max Activating Token Index: 419

Text #5

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.6461. Min Act: -0.0000

Data Index: 1556007 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.5920. Min Act: -0.0000

Data Index: 1535486 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.4448. Min Act: -0.0000

Data Index: 1484695 (Python Code)

Max Activating Token Index: 827

Text #8

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.4966. Min Act: -0.0000

Data Index: 1531490 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.5158. Min Act: -0.0000

Data Index: 1436337 (Python Code)

Max Activating Token Index: 792

Text #10

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.3654. Min Act: -0.0000

Data Index: 1408651 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.3385. Min Act: -0.0000

Data Index: 1633048 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.5837. Min Act: -0.0000

Data Index: 1509494 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.4331. Min Act: -0.0000

Data Index: 1582592 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.4296. Min Act: -0.0000

Data Index: 1445651 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.4328. Min Act: -0.0000

Data Index: 1641765 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.2902. Min Act: -0.0000

Data Index: 1626270 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.4036. Min Act: -0.0000

Data Index: 1466193 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.3988. Min Act: -0.0000

Data Index: 1448476 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 3.0541. Min Range: -3.0541

Max Act: 2.2675. Min Act: -0.0000

Data Index: 1566288 (Python Code)

Max Activating Token Index: 959