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

Dataset: The Pile

Neuron 2246 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: 3.3258. Min Range: -3.3258

Max Act: 3.1982. Min Act: -0.0000

Data Index: 1881821 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2745. Min Act: -0.0000

Data Index: 724121 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.8392. Min Act: -0.0000

Data Index: 1242816 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1261. Min Act: -0.0000

Data Index: 156114 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2225. Min Act: -0.0000

Data Index: 75073 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.3258. Min Act: -0.0000

Data Index: 1411271 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1510. Min Act: -0.0000

Data Index: 623931 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1513. Min Act: -0.0000

Data Index: 1005036 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0597. Min Act: -0.0000

Data Index: 1396426 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.7928. Min Act: -0.0000

Data Index: 651775 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0385. Min Act: -0.0000

Data Index: 433993 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.7750. Min Act: -0.0000

Data Index: 901450 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.8706. Min Act: -0.0000

Data Index: 804633 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.9864. Min Act: -0.0000

Data Index: 1005548 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.9616. Min Act: -0.0000

Data Index: 699259 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.7859. Min Act: -0.0000

Data Index: 802311 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.7407. Min Act: -0.0000

Data Index: 1920304 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.7614. Min Act: -0.0000

Data Index: 1460756 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.7518. Min Act: -0.0000

Data Index: 759670 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.7644. Min Act: -0.0000

Data Index: 804565 (The Pile)

Max Activating Token Index: 371