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

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

Neuron 4200 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: 3.0305. Min Range: -3.0305

Max Act: 3.0133. Min Act: -0.0000

Data Index: 1103431 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 3.0305. Min Range: -3.0305

Max Act: 3.0305. Min Act: -0.0000

Data Index: 389809 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.8816. Min Act: -0.0000

Data Index: 129406 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.5576. Min Act: -0.0000

Data Index: 1053775 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.7650. Min Act: -0.0000

Data Index: 1190675 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.4151. Min Act: -0.0000

Data Index: 1270550 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.3183. Min Act: -0.0000

Data Index: 1172268 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.2618. Min Act: -0.0000

Data Index: 96392 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 3.0305. Min Range: -3.0305

Max Act: 1.9886. Min Act: -0.0000

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.0594. Min Act: -0.0000

Data Index: 320599 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.0167. Min Act: -0.0000

Data Index: 112527 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.0021. Min Act: -0.0000

Data Index: 652734 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.0083. Min Act: -0.0000

Data Index: 535601 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 3.0305. Min Range: -3.0305

Max Act: 1.9263. Min Act: -0.0000

Data Index: 539579 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 3.0305. Min Range: -3.0305

Max Act: 2.0340. Min Act: -0.0000

Data Index: 1158662 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.0305. Min Range: -3.0305

Max Act: 1.9096. Min Act: -0.0000

Data Index: 383056 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 3.0305. Min Range: -3.0305

Max Act: 1.9110. Min Act: -0.0000

Data Index: 614720 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 3.0305. Min Range: -3.0305

Max Act: 1.9060. Min Act: -0.0000

Data Index: 1234691 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 3.0305. Min Range: -3.0305

Max Act: 1.9022. Min Act: -0.0000

Data Index: 699308 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.0305. Min Range: -3.0305

Max Act: 1.9850. Min Act: -0.0000

Data Index: 998410 (C4 (Web Text))

Max Activating Token Index: 851