Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 519 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.9038. Min Act: -0.0001

Data Index: 1049505 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.8808. Min Act: -0.0001

Data Index: 449509 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.7756. Min Act: -0.0001

Data Index: 757020 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.7870. Min Act: -0.0001

Data Index: 1313673 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.7453. Min Act: -0.0001

Data Index: 885777 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.7450. Min Act: -0.0001

Data Index: 780143 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.7598. Min Act: -0.0001

Data Index: 206195 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.7005. Min Act: -0.0001

Data Index: 853303 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.7428. Min Act: -0.0001

Data Index: 666280 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6827. Min Act: -0.0001

Data Index: 309460 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6344. Min Act: -0.0001

Data Index: 125414 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6484. Min Act: -0.0001

Data Index: 524506 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1052599 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6395. Min Act: -0.0001

Data Index: 1217917 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6572. Min Act: -0.0001

Data Index: 286080 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6148. Min Act: -0.0001

Data Index: 526187 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6533. Min Act: -0.0001

Data Index: 1075707 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.6191. Min Act: -0.0001

Data Index: 665421 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.5964. Min Act: -0.0001

Data Index: 237298 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.9038. Min Range: -0.9038

Max Act: 0.5924. Min Act: -0.0001

Data Index: 663172 (C4 (Web Text))

Max Activating Token Index: 241