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

Dataset: The Pile

Neuron 1210 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.3787. Min Act: -0.0001

Data Index: 1919869 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1658. Min Act: -0.0000

Data Index: 1366823 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1801. Min Act: -0.0000

Data Index: 236017 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1908392 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1354378 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1505511 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 1.3787. Min Range: -1.3787

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1877399 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0703. Min Act: -0.0000

Data Index: 321178 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0495. Min Act: -0.0000

Data Index: 279159 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0683. Min Act: -0.0000

Data Index: 916837 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1323412 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 1.3787. Min Range: -1.3787

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1451640 (The Pile)

Max Activating Token Index: 941

Text #12

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0542. Min Act: -0.0000

Data Index: 906895 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 1.3787. Min Range: -1.3787

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1299467 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.3787. Min Range: -1.3787

Max Act: 0.9678. Min Act: -0.0000

Data Index: 794376 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 1.3787. Min Range: -1.3787

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1737749 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0150. Min Act: -0.0000

Data Index: 538220 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 1.3787. Min Range: -1.3787

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1327105 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1208435 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 1.3787. Min Range: -1.3787

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1398453 (The Pile)

Max Activating Token Index: 135