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

Dataset: The Pile

Neuron 595 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.2068. Min Act: -0.0000

Data Index: 586599 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.3288. Min Act: -0.0000

Data Index: 299206 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1182397 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.2654. Min Act: -0.0000

Data Index: 1567603 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.2186. Min Act: -0.0000

Data Index: 221408 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1513. Min Act: -0.0000

Data Index: 611640 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.2068. Min Act: -0.0000

Data Index: 192407 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1157345 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1754. Min Act: -0.0000

Data Index: 339778 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1221219 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1566. Min Act: -0.0000

Data Index: 779811 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1271608 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1560351 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1916514 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1532. Min Act: -0.0000

Data Index: 68549 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1402150 (The Pile)

Max Activating Token Index: 364

Text #16

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1527421 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1228236 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1141231 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 1.3288. Min Range: -1.3288

Max Act: 1.1668. Min Act: -0.0000

Data Index: 898731 (The Pile)

Max Activating Token Index: 753