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

Dataset: The Pile

Neuron 2609 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1137. Min Range: -1.1137

Max Act: 1.1137. Min Act: -0.0000

Data Index: 154896 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 1.1137. Min Range: -1.1137

Max Act: 1.1099. Min Act: -0.0000

Data Index: 1434293 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 1.1137. Min Range: -1.1137

Max Act: 1.0770. Min Act: -0.0001

Data Index: 19293 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 1.1137. Min Range: -1.1137

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1499214 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1999953 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 1.1137. Min Range: -1.1137

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1828083 (The Pile)

Max Activating Token Index: 220

Text #6

Max Range: 1.1137. Min Range: -1.1137

Max Act: 1.0038. Min Act: -0.0001

Data Index: 1786638 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 1.1137. Min Range: -1.1137

Max Act: 1.0132. Min Act: -0.0000

Data Index: 625431 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9787. Min Act: -0.0000

Data Index: 206595 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9904. Min Act: -0.0000

Data Index: 307868 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9457. Min Act: 0.0000

Data Index: 1820705 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9562. Min Act: 0.0000

Data Index: 998145 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9296. Min Act: -0.0001

Data Index: 774926 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9347. Min Act: -0.0000

Data Index: 444664 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1893819 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1346952 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9480. Min Act: 0.0000

Data Index: 599010 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9442. Min Act: -0.0000

Data Index: 816186 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1722528 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.8538. Min Act: -0.0000

Data Index: 553930 (The Pile)

Max Activating Token Index: 789