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

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

Neuron 5220 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4886. Min Range: -3.4886

Max Act: 3.4886. Min Act: -0.0000

Data Index: 593009 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 3.4886. Min Range: -3.4886

Max Act: 3.4721. Min Act: -0.0000

Data Index: 828607 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.4886. Min Range: -3.4886

Max Act: 3.0247. Min Act: -0.0000

Data Index: 100413 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 3.4886. Min Range: -3.4886

Max Act: 3.1489. Min Act: -0.0000

Data Index: 70327 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 3.4886. Min Range: -3.4886

Max Act: 3.2953. Min Act: -0.0000

Data Index: 998813 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.9743. Min Act: -0.0000

Data Index: 1151996 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 3.4886. Min Range: -3.4886

Max Act: 3.1114. Min Act: -0.0000

Data Index: 639186 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 3.4886. Min Range: -3.4886

Max Act: 3.0896. Min Act: -0.0000

Data Index: 610889 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 3.4886. Min Range: -3.4886

Max Act: 3.1363. Min Act: -0.0001

Data Index: 261852 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.9688. Min Act: -0.0000

Data Index: 318588 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.8470. Min Act: -0.0001

Data Index: 840732 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.6874. Min Act: -0.0000

Data Index: 1120511 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.7205. Min Act: -0.0000

Data Index: 349148 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.6906. Min Act: -0.0001

Data Index: 58329 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.6484. Min Act: -0.0000

Data Index: 123627 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.7138. Min Act: -0.0000

Data Index: 15548 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.8264. Min Act: -0.0001

Data Index: 405460 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.4078. Min Act: -0.0000

Data Index: 542761 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.3534. Min Act: -0.0001

Data Index: 834386 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 3.4886. Min Range: -3.4886

Max Act: 2.3558. Min Act: -0.0000

Data Index: 669662 (C4 (Web Text))

Max Activating Token Index: 13