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

Dataset: The Pile

Neuron 344 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1218875 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5357. Min Act: -0.0000

Data Index: 893916 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5445. Min Act: -0.0000

Data Index: 227246 (The Pile)

Max Activating Token Index: 98

Text #3

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1700912 (The Pile)

Max Activating Token Index: 379

Text #4

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5188. Min Act: -0.0000

Data Index: 82036 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1092208 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1464510 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4516. Min Act: -0.0000

Data Index: 826082 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1301224 (The Pile)

Max Activating Token Index: 748

Text #9

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1636466 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1345167 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4588. Min Act: -0.0000

Data Index: 922706 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1437296 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1501424 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1487111 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3848. Min Act: -0.0000

Data Index: 1200867 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4562. Min Act: -0.0000

Data Index: 803100 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3958. Min Act: -0.0000

Data Index: 77419 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4109. Min Act: -0.0000

Data Index: 283341 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3965. Min Act: -0.0000

Data Index: 419991 (The Pile)

Max Activating Token Index: 178