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

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

Neuron 4020 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1103677 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2890. Min Act: -0.0000

Data Index: 430623 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2714. Min Act: -0.0000

Data Index: 469540 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2952. Min Act: -0.0000

Data Index: 685791 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2879. Min Act: -0.0000

Data Index: 827202 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2869. Min Act: -0.0000

Data Index: 6685 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2877. Min Act: -0.0000

Data Index: 951358 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2670. Min Act: -0.0000

Data Index: 804360 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2568. Min Act: -0.0000

Data Index: 563378 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2666. Min Act: -0.0000

Data Index: 456830 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1073942 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2589. Min Act: -0.0000

Data Index: 215663 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2366. Min Act: -0.0000

Data Index: 125019 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2583. Min Act: -0.0000

Data Index: 683051 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2342. Min Act: -0.0000

Data Index: 924763 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2639. Min Act: -0.0000

Data Index: 129798 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1336907 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2446. Min Act: -0.0000

Data Index: 612374 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1044303 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1176396 (C4 (Web Text))

Max Activating Token Index: 477