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

Dataset: The Pile

Neuron 138 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: 0.8091. Min Range: -0.8091

Max Act: 0.8091. Min Act: -0.0000

Data Index: 290269 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6654. Min Act: -0.0000

Data Index: 321644 (The Pile)

Max Activating Token Index: 550

Text #2

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6864. Min Act: -0.0000

Data Index: 358957 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6575. Min Act: -0.0000

Data Index: 467455 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6691. Min Act: -0.0000

Data Index: 452354 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1662150 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5647. Min Act: -0.0000

Data Index: 663976 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5770. Min Act: -0.0000

Data Index: 685110 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1222031 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5444. Min Act: -0.0000

Data Index: 208404 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5556. Min Act: -0.0000

Data Index: 729525 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5324. Min Act: -0.0000

Data Index: 64832 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1049212 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5431. Min Act: -0.0000

Data Index: 231394 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1854484 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.4860. Min Act: -0.0000

Data Index: 303552 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5164. Min Act: -0.0000

Data Index: 93042 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1445893 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.5444. Min Act: -0.0000

Data Index: 214079 (The Pile)

Max Activating Token Index: 196

Text #19

Max Range: 0.8091. Min Range: -0.8091

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1116026 (The Pile)

Max Activating Token Index: 1018