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

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

Neuron 4956 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.8021. Min Act: -0.0000

Data Index: 1494005 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.7591. Min Act: -0.0000

Data Index: 1603168 (Python Code)

Max Activating Token Index: 506

Text #2

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.5919. Min Act: -0.0000

Data Index: 265986 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.3478. Min Act: -0.0000

Data Index: 1015837 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.3931. Min Act: -0.0000

Data Index: 184365 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.3608. Min Act: -0.0000

Data Index: 801806 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.3245. Min Act: -0.0000

Data Index: 1147817 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.3037. Min Act: -0.0000

Data Index: 1072730 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.2909. Min Act: -0.0000

Data Index: 1080649 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.0322. Min Act: -0.0000

Data Index: 937442 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.2458. Min Act: -0.0000

Data Index: 736887 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.2458. Min Act: -0.0000

Data Index: 1094438 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.1204. Min Act: -0.0000

Data Index: 47530 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.2158. Min Act: -0.0000

Data Index: 562496 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.2390. Min Act: -0.0000

Data Index: 860140 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.0986. Min Act: -0.0000

Data Index: 1298611 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.0934. Min Act: -0.0000

Data Index: 1039187 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.2399. Min Act: -0.0000

Data Index: 609711 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.0978. Min Act: -0.0000

Data Index: 957506 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 2.8021. Min Range: -2.8021

Max Act: 2.1668. Min Act: -0.0000

Data Index: 633800 (C4 (Web Text))

Max Activating Token Index: 569