Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1784 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.3759. Min Act: -0.0001

Data Index: 837023 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0952. Min Act: -0.0001

Data Index: 1029949 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0614. Min Act: -0.0001

Data Index: 17398 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0253. Min Act: -0.0001

Data Index: 691726 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9359. Min Act: -0.0001

Data Index: 479080 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9281. Min Act: -0.0001

Data Index: 93218 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8946. Min Act: -0.0001

Data Index: 1298912 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9712. Min Act: -0.0001

Data Index: 169356 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9182. Min Act: -0.0001

Data Index: 606775 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9113. Min Act: -0.0001

Data Index: 1307840 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9557. Min Act: -0.0001

Data Index: 1211403 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8698. Min Act: -0.0001

Data Index: 83921 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8550. Min Act: -0.0001

Data Index: 221162 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8790. Min Act: -0.0001

Data Index: 841516 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8512. Min Act: -0.0001

Data Index: 844101 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8177. Min Act: -0.0001

Data Index: 484597 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.7899. Min Act: -0.0001

Data Index: 669605 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8513. Min Act: -0.0001

Data Index: 527315 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8267. Min Act: -0.0001

Data Index: 412557 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9667. Min Act: -0.0001

Data Index: 354468 (C4 (Web Text))

Max Activating Token Index: 837