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

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

Neuron 3315 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0677. Min Act: -0.0002

Data Index: 341325 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0002

Data Index: 620080 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0528. Min Act: -0.0002

Data Index: 95221 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1066535 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0520. Min Act: -0.0002

Data Index: 219718 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0541. Min Act: -0.0002

Data Index: 416864 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0579. Min Act: -0.0002

Data Index: 50665 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0592. Min Act: -0.0002

Data Index: 988523 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1346207 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0523. Min Act: -0.0002

Data Index: 252417 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1180810 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0652. Min Act: -0.0002

Data Index: 867313 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1110886 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0557. Min Act: -0.0002

Data Index: 552322 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0483. Min Act: -0.0002

Data Index: 996854 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0580. Min Act: -0.0002

Data Index: 192416 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1164647 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0516. Min Act: -0.0002

Data Index: 85574 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0516. Min Act: -0.0002

Data Index: 64078 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1106977 (C4 (Web Text))

Max Activating Token Index: 52