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

Dataset: The Pile

Neuron 1251 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: 0.4391. Min Range: -0.4391

Max Act: 0.4391. Min Act: -0.0000

Data Index: 179074 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4170. Min Act: -0.0000

Data Index: 188852 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4384. Min Act: 0.0001

Data Index: 106139 (The Pile)

Max Activating Token Index: 895

Text #3

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4077. Min Act: -0.0000

Data Index: 507394 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4202. Min Act: 0.0000

Data Index: 1537060 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4087. Min Act: 0.0000

Data Index: 695625 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4126. Min Act: -0.0000

Data Index: 821401 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1058801 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1261431 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1088222 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3540. Min Act: -0.0000

Data Index: 181127 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3561. Min Act: -0.0000

Data Index: 751253 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3522. Min Act: -0.0000

Data Index: 202162 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1618467 (The Pile)

Max Activating Token Index: 622

Text #14

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1685058 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3357. Min Act: -0.0000

Data Index: 842315 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1344040 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3448. Min Act: -0.0000

Data Index: 816307 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3258. Min Act: -0.0000

Data Index: 294252 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3326. Min Act: -0.0000

Data Index: 69036 (The Pile)

Max Activating Token Index: 296