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

Dataset: The Pile

Neuron 1373 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: 1.1071. Min Range: -1.1071

Max Act: 1.1071. Min Act: -0.0000

Data Index: 270780 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1800159 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1701423 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1906464 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9286. Min Act: -0.0000

Data Index: 252680 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.1071. Min Range: -1.1071

Max Act: 1.0044. Min Act: -0.0000

Data Index: 236335 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1572557 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8523. Min Act: -0.0000

Data Index: 963745 (The Pile)

Max Activating Token Index: 4

Text #8

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.9567. Min Act: -0.0000

Data Index: 865839 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8051. Min Act: -0.0000

Data Index: 224693 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8554. Min Act: -0.0000

Data Index: 663122 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8749. Min Act: -0.0000

Data Index: 576316 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8485. Min Act: -0.0000

Data Index: 908804 (The Pile)

Max Activating Token Index: 292

Text #13

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8218. Min Act: -0.0000

Data Index: 830435 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1320888 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1257737 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1152404 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1850399 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.7824. Min Act: -0.0000

Data Index: 888262 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 1.1071. Min Range: -1.1071

Max Act: 0.7542. Min Act: -0.0000

Data Index: 411245 (The Pile)

Max Activating Token Index: 615