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

Dataset: The Pile

Neuron 755 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: 0.7293. Min Range: -0.7293

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1681167 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1217947 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.5612. Min Act: -0.0000

Data Index: 933983 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.5438. Min Act: -0.0000

Data Index: 236373 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1105927 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1356981 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1812534 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4406. Min Act: -0.0000

Data Index: 962008 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4338. Min Act: -0.0000

Data Index: 293573 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1705882 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1552938 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1769423 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1844801 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1112332 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1117207 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4209. Min Act: -0.0000

Data Index: 381862 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1978648 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4260. Min Act: -0.0000

Data Index: 669843 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1259988 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1343773 (The Pile)

Max Activating Token Index: 215