Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2519 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0867. Min Act: -0.0001

Data Index: 1026314 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.1040. Min Act: -0.0001

Data Index: 920849 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9701. Min Act: -0.0001

Data Index: 1353587 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9854. Min Act: -0.0001

Data Index: 1267899 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9603. Min Act: -0.0001

Data Index: 1074806 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0066. Min Act: -0.0001

Data Index: 704513 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0047. Min Act: -0.0001

Data Index: 10867 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9977. Min Act: -0.0001

Data Index: 947691 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9480. Min Act: -0.0001

Data Index: 1137280 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9423. Min Act: -0.0001

Data Index: 271709 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9413. Min Act: -0.0001

Data Index: 1149226 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9357. Min Act: -0.0001

Data Index: 1628415 (Python Code)

Max Activating Token Index: 601

Text #12

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9581. Min Act: -0.0000

Data Index: 748943 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9591. Min Act: -0.0001

Data Index: 320183 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9059. Min Act: -0.0001

Data Index: 1146001 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9358. Min Act: -0.0001

Data Index: 316468 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9559. Min Act: -0.0001

Data Index: 178827 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9257. Min Act: -0.0001

Data Index: 1209675 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9083. Min Act: -0.0001

Data Index: 698417 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8896. Min Act: -0.0001

Data Index: 1635473 (Python Code)

Max Activating Token Index: 782