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

Dataset: The Pile

Neuron 3597 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.4700. Min Act: -0.0000

Data Index: 588048 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2017. Min Act: -0.0000

Data Index: 656002 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2623. Min Act: -0.0000

Data Index: 599730 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1673103 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1094124 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1748. Min Act: -0.0000

Data Index: 565503 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0579. Min Act: -0.0000

Data Index: 1337017 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1553256 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1091. Min Act: -0.0000

Data Index: 304353 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1820171 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1233643 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0644. Min Act: -0.0000

Data Index: 269820 (The Pile)

Max Activating Token Index: 229

Text #12

Max Range: 1.4700. Min Range: -1.4700

Max Act: 0.9754. Min Act: -0.0000

Data Index: 779322 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1293330 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0297. Min Act: -0.0000

Data Index: 550588 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 1.4700. Min Range: -1.4700

Max Act: 0.9358. Min Act: -0.0000

Data Index: 113245 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 1.4700. Min Range: -1.4700

Max Act: 0.9728. Min Act: -0.0000

Data Index: 252431 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 1.4700. Min Range: -1.4700

Max Act: 0.8594. Min Act: -0.0000

Data Index: 895948 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 1.4700. Min Range: -1.4700

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1144259 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.4700. Min Range: -1.4700

Max Act: 0.8669. Min Act: -0.0000

Data Index: 539710 (The Pile)

Max Activating Token Index: 265