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

Dataset: The Pile

Neuron 3147 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1546406 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.8476. Min Act: -0.0000

Data Index: 480592 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.8138. Min Act: -0.0000

Data Index: 621167 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7501. Min Act: -0.0000

Data Index: 89526 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7208. Min Act: -0.0000

Data Index: 160557 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7315. Min Act: -0.0000

Data Index: 782115 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1125462 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1904556 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7160. Min Act: -0.0000

Data Index: 21400 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1412069 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1253022 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1031512 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6858. Min Act: -0.0000

Data Index: 201469 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6809. Min Act: -0.0000

Data Index: 927026 (The Pile)

Max Activating Token Index: 917

Text #14

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6526. Min Act: -0.0000

Data Index: 378550 (The Pile)

Max Activating Token Index: 77

Text #15

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6754. Min Act: -0.0000

Data Index: 245257 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1117686 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6423. Min Act: -0.0000

Data Index: 637995 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1504956 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1770046 (The Pile)

Max Activating Token Index: 686