Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2864 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1247291 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1108. Min Act: -0.0001

Data Index: 390176 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1102978 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0946. Min Act: -0.0001

Data Index: 331548 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0931. Min Act: -0.0001

Data Index: 288050 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0992. Min Act: -0.0001

Data Index: 37135 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0885. Min Act: -0.0001

Data Index: 253093 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0825. Min Act: -0.0001

Data Index: 572883 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1149612 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0762. Min Act: -0.0001

Data Index: 621515 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0704. Min Act: -0.0001

Data Index: 621999 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0721. Min Act: -0.0001

Data Index: 292046 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0727. Min Act: -0.0001

Data Index: 955270 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0676. Min Act: -0.0001

Data Index: 579631 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0714. Min Act: -0.0001

Data Index: 108391 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0651. Min Act: -0.0001

Data Index: 974762 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0708. Min Act: -0.0001

Data Index: 518182 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0701. Min Act: -0.0001

Data Index: 920600 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0696. Min Act: -0.0001

Data Index: 947833 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0733. Min Act: -0.0001

Data Index: 117224 (C4 (Web Text))

Max Activating Token Index: 903