Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3349 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5817. Min Act: -0.0000

Data Index: 1056293 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5982. Min Act: -0.0000

Data Index: 1918273 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4385. Min Act: -0.0000

Data Index: 1126532 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.5093. Min Act: -0.0000

Data Index: 985927 (The Pile)

Max Activating Token Index: 813

Text #4

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.3657. Min Act: -0.0000

Data Index: 398280 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1172691 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1208809 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1970619 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1674673 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1790796 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2666. Min Act: -0.0000

Data Index: 94132 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1815606 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1202296 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.2055. Min Act: -0.0000

Data Index: 1490431 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.0191. Min Act: -0.0000

Data Index: 998314 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 1.5982. Min Range: -1.5982

Max Act: 0.9790. Min Act: -0.0000

Data Index: 402287 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1567860 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.0658. Min Act: -0.0000

Data Index: 1233649 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1802119 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 1.5982. Min Range: -1.5982

Max Act: 1.0538. Min Act: -0.0000

Data Index: 1631004 (The Pile)

Max Activating Token Index: 443