Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2025 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.5346. Min Act: -0.0001

Data Index: 1825231 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4080. Min Act: -0.0000

Data Index: 667959 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4022. Min Act: -0.0001

Data Index: 1684832 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3756. Min Act: -0.0001

Data Index: 1253193 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3779. Min Act: -0.0000

Data Index: 646926 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3586. Min Act: -0.0001

Data Index: 1297640 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1163167 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3512. Min Act: -0.0000

Data Index: 431277 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1468508 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1822739 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1910220 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3330. Min Act: -0.0000

Data Index: 241648 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1357005 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3102. Min Act: -0.0001

Data Index: 749507 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1241476 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3073. Min Act: -0.0000

Data Index: 708435 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1105570 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3161. Min Act: -0.0000

Data Index: 615775 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3022. Min Act: -0.0001

Data Index: 658158 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.2921. Min Act: -0.0001

Data Index: 89712 (The Pile)

Max Activating Token Index: 285