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

Dataset: The Pile

Neuron 1156 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.2468. Min Act: -0.0000

Data Index: 927334 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3515. Min Act: -0.0000

Data Index: 1466477 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.8386. Min Act: -0.0000

Data Index: 1216689 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.6542. Min Act: -0.0000

Data Index: 915553 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.1474. Min Act: -0.0000

Data Index: 686828 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.6891. Min Act: -0.0000

Data Index: 644266 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.2436. Min Act: -0.0000

Data Index: 776125 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.4672. Min Act: -0.0000

Data Index: 750178 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.5123. Min Act: -0.0000

Data Index: 1532387 (The Pile)

Max Activating Token Index: 726

Text #9

Max Range: 3.6542. Min Range: -3.6542

Max Act: 1.7664. Min Act: -0.0000

Data Index: 1471594 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.4531. Min Act: -0.0000

Data Index: 1238236 (The Pile)

Max Activating Token Index: 682

Text #11

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.3628. Min Act: -0.0000

Data Index: 926153 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.2458. Min Act: -0.0000

Data Index: 900503 (The Pile)

Max Activating Token Index: 777

Text #13

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.3952. Min Act: -0.0000

Data Index: 144300 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.4328. Min Act: -0.0000

Data Index: 144507 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 3.6542. Min Range: -3.6542

Max Act: 1.9545. Min Act: -0.0000

Data Index: 1081519 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 3.6542. Min Range: -3.6542

Max Act: 1.9418. Min Act: -0.0000

Data Index: 247262 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.4073. Min Act: -0.0000

Data Index: 609808 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.1322. Min Act: -0.0000

Data Index: 1007061 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.2894. Min Act: -0.0000

Data Index: 1606101 (The Pile)

Max Activating Token Index: 846