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

Dataset: The Pile

Neuron 3229 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: 1.5687. Min Range: -1.5687

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1339565 (The Pile)

Max Activating Token Index: 515

Text #1

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.5687. Min Act: -0.0000

Data Index: 888959 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.5243. Min Act: -0.0000

Data Index: 1798442 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.4833. Min Act: -0.0000

Data Index: 158218 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3704. Min Act: -0.0000

Data Index: 878055 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1887070 (The Pile)

Max Activating Token Index: 105

Text #6

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1499464 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1346508 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.4232. Min Act: -0.0000

Data Index: 1785437 (The Pile)

Max Activating Token Index: 688

Text #9

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1819256 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1547056 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3692. Min Act: -0.0000

Data Index: 666819 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3804. Min Act: -0.0000

Data Index: 553338 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.1694. Min Act: -0.0000

Data Index: 764974 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.2305. Min Act: -0.0000

Data Index: 1153018 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3409. Min Act: -0.0000

Data Index: 311174 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3363. Min Act: -0.0000

Data Index: 402553 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3868. Min Act: -0.0000

Data Index: 213433 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.4286. Min Act: -0.0000

Data Index: 50475 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.2863. Min Act: -0.0000

Data Index: 1622698 (The Pile)

Max Activating Token Index: 676