Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 85 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0006

Data Index: 730690 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1167078 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0042. Min Act: -0.0006

Data Index: 261432 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0041. Min Act: -0.0006

Data Index: 887237 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0041. Min Act: -0.0006

Data Index: 805163 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0041. Min Act: -0.0006

Data Index: 359991 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0039. Min Act: -0.0006

Data Index: 185315 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0039. Min Act: -0.0006

Data Index: 274688 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0038. Min Act: -0.0006

Data Index: 397374 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 153977 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 468305 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 970441 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 1004988 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 811483 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0006

Data Index: 1353606 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 545432 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0006

Data Index: 549859 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 320304 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0007

Data Index: 502584 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0006

Data Index: 1280221 (C4 (Web Text))

Max Activating Token Index: 341