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

Dataset: The Pile

Neuron 2849 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5293. Min Act: -0.0000

Data Index: 840700 (The Pile)

Max Activating Token Index: 212

Text #1

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5662. Min Act: -0.0000

Data Index: 194593 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1195719 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1500197 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5705. Min Act: -0.0000

Data Index: 193114 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1427014 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4903. Min Act: -0.0000

Data Index: 169434 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1517162 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1061727 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1566433 (The Pile)

Max Activating Token Index: 857

Text #10

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1844772 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4370. Min Act: -0.0000

Data Index: 689076 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1782890 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4301. Min Act: -0.0000

Data Index: 605753 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1128479 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1271946 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1759286 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1078987 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1056841 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1434813 (The Pile)

Max Activating Token Index: 672