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

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

Neuron 1155 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.8221. Min Act: -0.0001

Data Index: 1423549 (Python Code)

Max Activating Token Index: 549

Text #1

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6618. Min Act: -0.0001

Data Index: 258334 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1194325 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6334. Min Act: -0.0001

Data Index: 1409432 (Python Code)

Max Activating Token Index: 440

Text #4

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5672. Min Act: -0.0001

Data Index: 639053 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5507. Min Act: -0.0001

Data Index: 319530 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5479. Min Act: -0.0001

Data Index: 886220 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5092. Min Act: -0.0001

Data Index: 36512 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5012. Min Act: -0.0001

Data Index: 905973 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5124. Min Act: -0.0001

Data Index: 1622914 (Python Code)

Max Activating Token Index: 929

Text #10

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5266. Min Act: -0.0001

Data Index: 759418 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5058. Min Act: -0.0001

Data Index: 999791 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5096. Min Act: -0.0001

Data Index: 1250749 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5206. Min Act: -0.0001

Data Index: 726762 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5014. Min Act: -0.0001

Data Index: 861066 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5351. Min Act: -0.0001

Data Index: 709556 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5262. Min Act: -0.0001

Data Index: 1101013 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5614. Min Act: -0.0001

Data Index: 1162765 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.4687. Min Act: -0.0001

Data Index: 600884 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5151. Min Act: -0.0001

Data Index: 1327451 (C4 (Web Text))

Max Activating Token Index: 286