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

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

Neuron 786 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: 3.8774. Min Range: -3.8774

Max Act: 3.8774. Min Act: -0.0001

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.5033. Min Act: -0.0001

Data Index: 1197196 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.7522. Min Act: -0.0001

Data Index: 1017610 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.5349. Min Act: -0.0001

Data Index: 28494 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.8316. Min Act: -0.0001

Data Index: 233480 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.6516. Min Act: -0.0001

Data Index: 1028458 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.4744. Min Act: -0.0001

Data Index: 779941 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.5584. Min Act: -0.0001

Data Index: 117919 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.4603. Min Act: -0.0001

Data Index: 291450 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.3152. Min Act: -0.0001

Data Index: 960424 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.3027. Min Act: -0.0001

Data Index: 657437 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.2842. Min Act: -0.0001

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 3.8774. Min Range: -3.8774

Max Act: 2.9349. Min Act: -0.0001

Data Index: 133273 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 3.8774. Min Range: -3.8774

Max Act: 2.9805. Min Act: -0.0001

Data Index: 575264 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.1985. Min Act: -0.0001

Data Index: 918722 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 3.8774. Min Range: -3.8774

Max Act: 2.8930. Min Act: -0.0001

Data Index: 346129 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 3.8774. Min Range: -3.8774

Max Act: 2.8790. Min Act: -0.0001

Data Index: 579912 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 3.8774. Min Range: -3.8774

Max Act: 2.8748. Min Act: -0.0001

Data Index: 1289522 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 3.8774. Min Range: -3.8774

Max Act: 3.0541. Min Act: -0.0001

Data Index: 1170782 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.8774. Min Range: -3.8774

Max Act: 2.9016. Min Act: -0.0001

Data Index: 676460 (C4 (Web Text))

Max Activating Token Index: 26