Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3074. Min Range: -1.3074

Max Act: 1.3074. Min Act: -0.0000

Data Index: 485658 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 1.3074. Min Range: -1.3074

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1863032 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 1.3074. Min Range: -1.3074

Max Act: 1.1000. Min Act: -0.0000

Data Index: 826768 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.8335. Min Act: -0.0000

Data Index: 552840 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.9568. Min Act: -0.0000

Data Index: 882593 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1885684 (The Pile)

Max Activating Token Index: 753

Text #6

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.8420. Min Act: -0.0000

Data Index: 225647 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.7660. Min Act: -0.0000

Data Index: 341828 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1220115 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1566478 (The Pile)

Max Activating Token Index: 964

Text #10

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1574383 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1353878 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.6949. Min Act: -0.0000

Data Index: 738754 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.7415. Min Act: -0.0000

Data Index: 498645 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.7080. Min Act: -0.0000

Data Index: 115097 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.6689. Min Act: -0.0000

Data Index: 889915 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.6933. Min Act: -0.0000

Data Index: 831645 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1312369 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1907925 (The Pile)

Max Activating Token Index: 735

Text #19

Max Range: 1.3074. Min Range: -1.3074

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1070024 (The Pile)

Max Activating Token Index: 1020