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

Dataset: The Pile

Neuron 2920 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: 3.0051. Min Range: -3.0051

Max Act: 3.0051. Min Act: -0.0000

Data Index: 962940 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.8152. Min Act: -0.0000

Data Index: 1365200 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.6977. Min Act: -0.0000

Data Index: 1123153 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.7059. Min Act: -0.0000

Data Index: 563827 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.4231. Min Act: -0.0000

Data Index: 1887577 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1542656 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.8179. Min Act: -0.0000

Data Index: 135378 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.5168. Min Act: -0.0000

Data Index: 1885197 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.4453. Min Act: -0.0000

Data Index: 1905290 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.4327. Min Act: -0.0000

Data Index: 391852 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.2423. Min Act: -0.0000

Data Index: 368843 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.1163. Min Act: -0.0000

Data Index: 1458688 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.7938. Min Act: -0.0000

Data Index: 493029 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.2412. Min Act: -0.0000

Data Index: 1449319 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.0726. Min Act: -0.0000

Data Index: 1190398 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.2008. Min Act: -0.0000

Data Index: 299591 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.5893. Min Act: -0.0000

Data Index: 1542740 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.4127. Min Act: -0.0000

Data Index: 185124 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.2445. Min Act: -0.0000

Data Index: 1633026 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 3.0051. Min Range: -3.0051

Max Act: 2.0687. Min Act: -0.0000

Data Index: 662728 (The Pile)

Max Activating Token Index: 517