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

Dataset: The Pile

Neuron 3087 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.4711. Min Act: -0.0000

Data Index: 977227 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.6647. Min Act: -0.0000

Data Index: 1716568 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.6421. Min Act: -0.0000

Data Index: 1724609 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1486991 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.3842. Min Act: -0.0000

Data Index: 422920 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1127642 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.2022. Min Act: -0.0000

Data Index: 338069 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.3001. Min Act: -0.0000

Data Index: 165996 (The Pile)

Max Activating Token Index: 761

Text #8

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.2855. Min Act: -0.0000

Data Index: 19665 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.2555. Min Act: -0.0000

Data Index: 112734 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.2520. Min Act: -0.0000

Data Index: 899017 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.1726. Min Act: -0.0000

Data Index: 604406 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.2459. Min Act: -0.0000

Data Index: 1928249 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1033046 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.3018. Min Act: -0.0000

Data Index: 649548 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1639571 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1467096 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.1344. Min Act: -0.0000

Data Index: 462419 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.1743. Min Act: -0.0000

Data Index: 398741 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 1.6647. Min Range: -1.6647

Max Act: 1.0873. Min Act: -0.0000

Data Index: 491829 (The Pile)

Max Activating Token Index: 707