Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2641 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.7120. Min Act: -0.0001

Data Index: 776468 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6797. Min Act: -0.0001

Data Index: 42216 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6012. Min Act: -0.0001

Data Index: 855578 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5631. Min Act: -0.0001

Data Index: 854665 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6076. Min Act: -0.0001

Data Index: 739046 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6008. Min Act: -0.0001

Data Index: 1138269 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5397. Min Act: -0.0001

Data Index: 765036 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5332. Min Act: -0.0001

Data Index: 256533 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5433. Min Act: -0.0001

Data Index: 733613 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5230. Min Act: -0.0001

Data Index: 959824 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5048. Min Act: -0.0001

Data Index: 748960 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4804. Min Act: -0.0001

Data Index: 645405 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4473. Min Act: -0.0001

Data Index: 72633 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4559. Min Act: -0.0001

Data Index: 448693 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4668. Min Act: -0.0001

Data Index: 669236 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4642. Min Act: -0.0001

Data Index: 328893 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4595. Min Act: -0.0001

Data Index: 524754 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4601. Min Act: -0.0001

Data Index: 815691 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4981. Min Act: -0.0001

Data Index: 201554 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4552. Min Act: -0.0001

Data Index: 920142 (C4 (Web Text))

Max Activating Token Index: 691