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

Dataset: The Pile

Neuron 3974 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: 0.4728. Min Range: -0.4728

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1603662 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.4283. Min Act: -0.0000

Data Index: 384186 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3761. Min Act: -0.0000

Data Index: 652877 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3739. Min Act: 0.0000

Data Index: 1045590 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1937025 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3726. Min Act: -0.0000

Data Index: 937935 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1630067 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3373. Min Act: -0.0000

Data Index: 430199 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1338055 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3404. Min Act: -0.0000

Data Index: 890921 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3259. Min Act: -0.0000

Data Index: 214057 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1682352 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3168. Min Act: 0.0000

Data Index: 1297220 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3077. Min Act: -0.0000

Data Index: 674144 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3340. Min Act: -0.0000

Data Index: 481607 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.2999. Min Act: 0.0000

Data Index: 651603 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1778781 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.2874. Min Act: -0.0000

Data Index: 317936 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.2827. Min Act: -0.0000

Data Index: 29674 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.2922. Min Act: -0.0000

Data Index: 780108 (The Pile)

Max Activating Token Index: 510