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

Dataset: The Pile

Neuron 3911 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.7403. Min Act: -0.0000

Data Index: 1458172 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.6339. Min Act: -0.0000

Data Index: 843581 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.7085. Min Act: -0.0000

Data Index: 667615 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1924169 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.5077. Min Act: -0.0000

Data Index: 109003 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1002835 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.5421. Min Act: -0.0000

Data Index: 412742 (The Pile)

Max Activating Token Index: 887

Text #7

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.4183. Min Act: -0.0000

Data Index: 1751562 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1783791 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1769954 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.2635. Min Act: -0.0000

Data Index: 35879 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.3325. Min Act: -0.0000

Data Index: 957511 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.1185. Min Act: -0.0000

Data Index: 156541 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.0459. Min Act: -0.0000

Data Index: 459034 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.2057. Min Act: -0.0000

Data Index: 78046 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1103850 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.1486. Min Act: -0.0000

Data Index: 1760198 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1665582 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 1.7403. Min Range: -1.7403

Max Act: 0.8765. Min Act: -0.0000

Data Index: 425745 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 1.7403. Min Range: -1.7403

Max Act: 1.1453. Min Act: -0.0000

Data Index: 524707 (The Pile)

Max Activating Token Index: 235