Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5368 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2491. Min Act: -0.0000

Data Index: 335283 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.3339. Min Act: -0.0000

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2070. Min Act: -0.0000

Data Index: 78768 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.2379. Min Act: -0.0000

Data Index: 538852 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.1072. Min Act: -0.0000

Data Index: 240808 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.1433. Min Act: -0.0000

Data Index: 815479 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9771. Min Act: -0.0000

Data Index: 273298 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1272435 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1453129 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.1274. Min Act: -0.0000

Data Index: 254381 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9885. Min Act: -0.0000

Data Index: 461056 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1233261 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0241. Min Act: -0.0000

Data Index: 934511 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1217272 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.3339. Min Range: -1.3339

Max Act: 1.0094. Min Act: -0.0000

Data Index: 226025 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9784. Min Act: -0.0000

Data Index: 421637 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1236138 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9657. Min Act: -0.0000

Data Index: 828973 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 1.3339. Min Range: -1.3339

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1525337 (Python Code)

Max Activating Token Index: 682