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

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

Neuron 321 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.4162. Min Act: 0.0000

Data Index: 1259301 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3959. Min Act: -0.0000

Data Index: 214086 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1022320 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1575466 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3371. Min Act: -0.0000

Data Index: 562647 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1179326 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3404. Min Act: -0.0000

Data Index: 173572 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1025458 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3294. Min Act: -0.0000

Data Index: 139157 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2967. Min Act: -0.0000

Data Index: 892052 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1316283 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2967. Min Act: -0.0000

Data Index: 307585 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2700. Min Act: -0.0000

Data Index: 166258 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2799. Min Act: -0.0000

Data Index: 49870 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1597370 (Python Code)

Max Activating Token Index: 609

Text #15

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2668. Min Act: -0.0000

Data Index: 843640 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2541. Min Act: -0.0000

Data Index: 908727 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2317. Min Act: -0.0000

Data Index: 788885 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1579947 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2609. Min Act: -0.0000

Data Index: 328630 (C4 (Web Text))

Max Activating Token Index: 941