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

Dataset: The Pile

Neuron 4977 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2105. Min Range: -4.2105

Max Act: 4.2105. Min Act: -0.0000

Data Index: 456691 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.8271. Min Act: -0.0000

Data Index: 975809 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.9705. Min Act: -0.0000

Data Index: 1527375 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.8626. Min Act: -0.0000

Data Index: 423832 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.4024. Min Act: -0.0000

Data Index: 781837 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.8830. Min Act: -0.0000

Data Index: 513717 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.6746. Min Act: -0.0000

Data Index: 479875 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.2546. Min Act: -0.0000

Data Index: 1847522 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.6065. Min Act: -0.0000

Data Index: 909914 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.3146. Min Act: -0.0000

Data Index: 1020616 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.2098. Min Act: -0.0000

Data Index: 73191 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.2451. Min Act: -0.0000

Data Index: 428052 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.2743. Min Act: -0.0000

Data Index: 1030959 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.0665. Min Act: -0.0000

Data Index: 810818 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.3263. Min Act: -0.0000

Data Index: 1191550 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.1705. Min Act: -0.0000

Data Index: 1639866 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.3041. Min Act: -0.0000

Data Index: 442350 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 4.2105. Min Range: -4.2105

Max Act: 2.9690. Min Act: -0.0000

Data Index: 579182 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 4.2105. Min Range: -4.2105

Max Act: 3.1072. Min Act: -0.0000

Data Index: 1292095 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 4.2105. Min Range: -4.2105

Max Act: 2.9233. Min Act: -0.0000

Data Index: 1507978 (The Pile)

Max Activating Token Index: 1004