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

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

Neuron 1819 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9608. Min Act: -0.0003

Data Index: 1114615 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8909. Min Act: -0.0003

Data Index: 571702 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9799. Min Act: -0.0003

Data Index: 742289 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9021. Min Act: -0.0003

Data Index: 1100952 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8229. Min Act: -0.0003

Data Index: 298689 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8695. Min Act: -0.0003

Data Index: 714136 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8097. Min Act: -0.0003

Data Index: 885233 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8720. Min Act: -0.0003

Data Index: 33606 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7648. Min Act: -0.0003

Data Index: 865022 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8758. Min Act: -0.0003

Data Index: 1030695 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8216. Min Act: -0.0003

Data Index: 1018793 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8451. Min Act: -0.0003

Data Index: 176408 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8430. Min Act: -0.0003

Data Index: 978283 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7795. Min Act: -0.0003

Data Index: 460867 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8858. Min Act: -0.0003

Data Index: 789382 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7620. Min Act: -0.0003

Data Index: 485218 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8866. Min Act: -0.0003

Data Index: 196122 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8092. Min Act: -0.0003

Data Index: 325750 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8091. Min Act: -0.0003

Data Index: 23768 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8314. Min Act: -0.0003

Data Index: 145037 (C4 (Web Text))

Max Activating Token Index: 270