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

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

Neuron 5404 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4141. Min Act: -0.0001

Data Index: 1008253 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4244. Min Act: -0.0001

Data Index: 495536 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4581. Min Act: -0.0001

Data Index: 850546 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4002. Min Act: -0.0001

Data Index: 546839 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4156. Min Act: -0.0001

Data Index: 143373 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4002. Min Act: -0.0001

Data Index: 176583 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.2853. Min Act: -0.0001

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3586. Min Act: -0.0001

Data Index: 862215 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4270. Min Act: -0.0001

Data Index: 770879 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3762. Min Act: -0.0002

Data Index: 896179 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3834. Min Act: -0.0001

Data Index: 494751 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3988. Min Act: -0.0002

Data Index: 1310038 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4243. Min Act: -0.0001

Data Index: 616469 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4031. Min Act: -0.0001

Data Index: 182467 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3875. Min Act: -0.0001

Data Index: 728218 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3826. Min Act: -0.0001

Data Index: 501292 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3931. Min Act: -0.0001

Data Index: 33553 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3696. Min Act: -0.0001

Data Index: 1284724 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.3557. Min Act: -0.0001

Data Index: 571538 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.4581. Min Range: -0.4581

Max Act: 0.4123. Min Act: -0.0001

Data Index: 39445 (C4 (Web Text))

Max Activating Token Index: 64