Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 645 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1231999 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0575. Min Act: -0.0002

Data Index: 843628 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0564. Min Act: -0.0002

Data Index: 781549 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0002

Data Index: 397120 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0564. Min Act: -0.0001

Data Index: 978577 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0542. Min Act: -0.0001

Data Index: 46004 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0550. Min Act: -0.0002

Data Index: 747074 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0514. Min Act: -0.0002

Data Index: 142897 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0531. Min Act: -0.0002

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0560. Min Act: -0.0002

Data Index: 88973 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1136954 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0527. Min Act: -0.0002

Data Index: 467365 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0536. Min Act: -0.0002

Data Index: 840542 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0540. Min Act: -0.0002

Data Index: 308976 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0511. Min Act: -0.0002

Data Index: 753498 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0519. Min Act: -0.0001

Data Index: 516438 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0526. Min Act: -0.0002

Data Index: 366393 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0510. Min Act: -0.0002

Data Index: 671223 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0527. Min Act: -0.0001

Data Index: 935068 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0523. Min Act: -0.0002

Data Index: 646358 (C4 (Web Text))

Max Activating Token Index: 768