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

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

Neuron 31 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0960. Min Range: -2.0960

Max Act: 2.0960. Min Act: -0.0000

Data Index: 1007984 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.7306. Min Act: -0.0000

Data Index: 1098227 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.6666. Min Act: -0.0000

Data Index: 597093 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.6655. Min Act: -0.0000

Data Index: 381021 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.7392. Min Act: -0.0000

Data Index: 1116222 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1259065 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.4391. Min Act: -0.0000

Data Index: 1061965 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.5487. Min Act: -0.0000

Data Index: 894065 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.5428. Min Act: -0.0000

Data Index: 1232677 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.6125. Min Act: -0.0000

Data Index: 970594 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.5308. Min Act: -0.0000

Data Index: 905927 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.4954. Min Act: -0.0000

Data Index: 936847 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.5635. Min Act: -0.0000

Data Index: 356986 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.2803. Min Act: -0.0000

Data Index: 677308 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.2666. Min Act: 0.0000

Data Index: 546012 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.3973. Min Act: -0.0000

Data Index: 143233 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.3962. Min Act: -0.0000

Data Index: 948805 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.3926. Min Act: -0.0000

Data Index: 666024 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.2945. Min Act: -0.0000

Data Index: 534151 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 2.0960. Min Range: -2.0960

Max Act: 1.3144. Min Act: 0.0000

Data Index: 205009 (C4 (Web Text))

Max Activating Token Index: 680