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

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

Neuron 1777 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4666. Min Act: -0.0000

Data Index: 315200 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1036821 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3370. Min Act: -0.0000

Data Index: 152010 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3498. Min Act: -0.0000

Data Index: 24091 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3575. Min Act: -0.0000

Data Index: 742789 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3265. Min Act: -0.0000

Data Index: 718616 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3497. Min Act: -0.0000

Data Index: 382570 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3500. Min Act: -0.0000

Data Index: 285802 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3537. Min Act: -0.0000

Data Index: 256154 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3493. Min Act: -0.0000

Data Index: 477160 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1078491 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3347. Min Act: -0.0000

Data Index: 173025 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3589. Min Act: -0.0000

Data Index: 248795 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3412. Min Act: -0.0000

Data Index: 866434 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3270. Min Act: -0.0000

Data Index: 829367 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3342. Min Act: -0.0000

Data Index: 226224 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3359. Min Act: -0.0000

Data Index: 84482 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1102212 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1183153 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3081. Min Act: -0.0000

Data Index: 539298 (C4 (Web Text))

Max Activating Token Index: 39