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

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

Neuron 3252 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: 1.6738. Min Range: -1.6738

Max Act: 1.6738. Min Act: -0.0001

Data Index: 770197 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.3688. Min Act: -0.0001

Data Index: 1113274 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1455. Min Act: -0.0001

Data Index: 244499 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1957. Min Act: -0.0001

Data Index: 185561 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.2228. Min Act: -0.0001

Data Index: 1349042 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1845. Min Act: -0.0001

Data Index: 678642 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1805. Min Act: -0.0001

Data Index: 1154586 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1328. Min Act: -0.0001

Data Index: 448130 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1297. Min Act: -0.0001

Data Index: 90148 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1560. Min Act: -0.0001

Data Index: 614633 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.2045. Min Act: -0.0001

Data Index: 1227905 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.0615. Min Act: -0.0001

Data Index: 1276441 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.0467. Min Act: -0.0001

Data Index: 926517 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1082. Min Act: -0.0001

Data Index: 298651 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.0807. Min Act: -0.0001

Data Index: 577674 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.0453. Min Act: -0.0001

Data Index: 683779 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.1351. Min Act: -0.0001

Data Index: 1259673 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.0982. Min Act: -0.0001

Data Index: 920560 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.0625. Min Act: -0.0001

Data Index: 747606 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.0865. Min Act: -0.0001

Data Index: 185792 (C4 (Web Text))

Max Activating Token Index: 423