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

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

Neuron 1356 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: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0002

Data Index: 606797 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0572. Min Act: -0.0002

Data Index: 132627 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0574. Min Act: -0.0001

Data Index: 684054 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0563. Min Act: -0.0002

Data Index: 941786 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0560. Min Act: -0.0002

Data Index: 425570 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0570. Min Act: -0.0001

Data Index: 786258 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1302082 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1151381 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0560. Min Act: -0.0002

Data Index: 472056 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0551. Min Act: -0.0002

Data Index: 166433 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1259873 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0545. Min Act: -0.0001

Data Index: 705311 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0552. Min Act: -0.0002

Data Index: 252581 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1268107 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1127540 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0545. Min Act: -0.0002

Data Index: 437892 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0530. Min Act: -0.0001

Data Index: 438640 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0532. Min Act: -0.0002

Data Index: 638925 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0528. Min Act: -0.0001

Data Index: 410384 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0509. Min Act: -0.0002

Data Index: 848188 (C4 (Web Text))

Max Activating Token Index: 973