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

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

Neuron 86 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: 2.2809. Min Range: -2.2809

Max Act: 2.2809. Min Act: -0.0001

Data Index: 864549 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 2.2809. Min Range: -2.2809

Max Act: 2.2657. Min Act: -0.0001

Data Index: 294767 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 2.2809. Min Range: -2.2809

Max Act: 2.1634. Min Act: -0.0000

Data Index: 331838 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 2.2809. Min Range: -2.2809

Max Act: 2.0468. Min Act: -0.0000

Data Index: 1099360 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8307. Min Act: -0.0001

Data Index: 435942 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.9199. Min Act: -0.0000

Data Index: 1106062 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8395. Min Act: -0.0000

Data Index: 52410 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8192. Min Act: -0.0001

Data Index: 1046550 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8252. Min Act: -0.0000

Data Index: 162870 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8115. Min Act: -0.0000

Data Index: 807359 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8135. Min Act: -0.0000

Data Index: 102029 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.9048. Min Act: -0.0001

Data Index: 162997 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.7642. Min Act: -0.0001

Data Index: 3397 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.7355. Min Act: -0.0000

Data Index: 456265 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8870. Min Act: -0.0001

Data Index: 1332695 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.6899. Min Act: -0.0000

Data Index: 87678 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8996. Min Act: -0.0001

Data Index: 871380 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.4168. Min Act: -0.0000

Data Index: 526031 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.8374. Min Act: -0.0000

Data Index: 919413 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 2.2809. Min Range: -2.2809

Max Act: 1.6664. Min Act: -0.0001

Data Index: 84514 (C4 (Web Text))

Max Activating Token Index: 947