Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3272 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0487. Min Range: -5.0487

Max Act: 5.0487. Min Act: -0.0001

Data Index: 613675 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.6752. Min Act: -0.0001

Data Index: 812644 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.6680. Min Act: -0.0001

Data Index: 40427 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.6252. Min Act: -0.0001

Data Index: 888219 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.7078. Min Act: -0.0001

Data Index: 66151 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.8711. Min Act: -0.0001

Data Index: 707473 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.6855. Min Act: -0.0001

Data Index: 922433 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.8349. Min Act: -0.0001

Data Index: 903558 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.4849. Min Act: -0.0001

Data Index: 825562 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.3120. Min Act: -0.0001

Data Index: 626415 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.5868. Min Act: -0.0001

Data Index: 1320558 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.3343. Min Act: -0.0001

Data Index: 895625 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.5258. Min Act: -0.0001

Data Index: 1202048 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.7028. Min Act: -0.0001

Data Index: 333626 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.5310. Min Act: -0.0001

Data Index: 1320383 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.1630. Min Act: -0.0001

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.2879. Min Act: -0.0001

Data Index: 562927 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.1113. Min Act: -0.0001

Data Index: 1038613 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.1112. Min Act: -0.0001

Data Index: 262922 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 5.0487. Min Range: -5.0487

Max Act: 4.0898. Min Act: -0.0001

Data Index: 906460 (C4 (Web Text))

Max Activating Token Index: 841