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

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

Neuron 4752 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3997. Min Act: -0.0002

Data Index: 230626 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3952. Min Act: -0.0002

Data Index: 1089441 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3609. Min Act: -0.0002

Data Index: 1342860 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3712. Min Act: -0.0002

Data Index: 317753 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3521. Min Act: -0.0002

Data Index: 31589 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3607. Min Act: -0.0002

Data Index: 275199 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3281. Min Act: -0.0002

Data Index: 545837 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3055. Min Act: -0.0002

Data Index: 736620 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2949. Min Act: -0.0002

Data Index: 47093 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3138. Min Act: -0.0002

Data Index: 1202454 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3138. Min Act: -0.0002

Data Index: 16225 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3037. Min Act: -0.0002

Data Index: 87551 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3027. Min Act: -0.0002

Data Index: 1062847 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3021. Min Act: -0.0002

Data Index: 169295 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3027. Min Act: -0.0002

Data Index: 1052977 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3124. Min Act: -0.0002

Data Index: 1351895 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2975. Min Act: -0.0001

Data Index: 1356018 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2800. Min Act: -0.0002

Data Index: 334643 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3054. Min Act: -0.0002

Data Index: 295769 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2926. Min Act: -0.0002

Data Index: 218375 (C4 (Web Text))

Max Activating Token Index: 568