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

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

Neuron 697 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.7681. Min Act: -0.0001

Data Index: 597502 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6861. Min Act: -0.0001

Data Index: 238223 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6854. Min Act: -0.0001

Data Index: 1342351 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6798. Min Act: -0.0001

Data Index: 636576 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5950. Min Act: -0.0001

Data Index: 452603 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6118. Min Act: -0.0001

Data Index: 905520 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6327. Min Act: -0.0001

Data Index: 669407 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6123. Min Act: -0.0001

Data Index: 836252 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5743. Min Act: -0.0001

Data Index: 874249 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6195. Min Act: -0.0001

Data Index: 280790 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5795. Min Act: -0.0001

Data Index: 893697 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5765. Min Act: -0.0001

Data Index: 1264429 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.6104. Min Act: -0.0001

Data Index: 982199 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5759. Min Act: -0.0001

Data Index: 165353 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5555. Min Act: -0.0001

Data Index: 454654 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1314692 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5443. Min Act: -0.0001

Data Index: 1174955 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1191498 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5359. Min Act: -0.0001

Data Index: 145254 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.7681. Min Range: -0.7681

Max Act: 0.5489. Min Act: -0.0001

Data Index: 717111 (C4 (Web Text))

Max Activating Token Index: 531