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

Dataset: The Pile

Neuron 1150 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: 0.7542. Min Range: -0.7542

Max Act: 0.7542. Min Act: -0.0000

Data Index: 923239 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.7536. Min Act: -0.0000

Data Index: 726510 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.7262. Min Act: -0.0000

Data Index: 87896 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6417. Min Act: -0.0000

Data Index: 7244 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6310. Min Act: -0.0000

Data Index: 401310 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1487117 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6252. Min Act: -0.0000

Data Index: 487122 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6359. Min Act: -0.0000

Data Index: 344303 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1271344 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5990. Min Act: -0.0000

Data Index: 243826 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5728. Min Act: -0.0000

Data Index: 890513 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1304584 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5575. Min Act: -0.0000

Data Index: 799239 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1995440 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1105557 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1747428 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1890984 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1040240 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5394. Min Act: -0.0000

Data Index: 582051 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5475. Min Act: -0.0000

Data Index: 431689 (The Pile)

Max Activating Token Index: 824