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

Dataset: The Pile

Neuron 3164 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: 0.5266. Min Range: -0.5266

Max Act: 0.5266. Min Act: -0.0000

Data Index: 735512 (The Pile)

Max Activating Token Index: 383

Text #1

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1732762 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1218247 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1769337 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1183263 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1197447 (The Pile)

Max Activating Token Index: 904

Text #6

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.4315. Min Act: 0.0000

Data Index: 644873 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.4043. Min Act: 0.0000

Data Index: 895858 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3575. Min Act: 0.0000

Data Index: 996353 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1232503 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1651679 (The Pile)

Max Activating Token Index: 702

Text #11

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1300210 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1635472 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1241680 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1158871 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1737659 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1359302 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3905. Min Act: -0.0000

Data Index: 767250 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3613. Min Act: -0.0000

Data Index: 120347 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.5266. Min Range: -0.5266

Max Act: 0.3593. Min Act: 0.0000

Data Index: 1295762 (The Pile)

Max Activating Token Index: 475