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

Dataset: The Pile

Neuron 3735 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: 5.7939. Min Range: -5.7939

Max Act: 5.7701. Min Act: -0.0000

Data Index: 612996 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.7939. Min Act: -0.0000

Data Index: 902055 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.4888. Min Act: -0.0000

Data Index: 756815 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.2616. Min Act: -0.0000

Data Index: 186435 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.3762. Min Act: -0.0000

Data Index: 1744257 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.3338. Min Act: -0.0000

Data Index: 127803 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.1319. Min Act: -0.0000

Data Index: 45266 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.0781. Min Act: -0.0000

Data Index: 480780 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.2167. Min Act: -0.0000

Data Index: 801741 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.1524. Min Act: -0.0000

Data Index: 1174009 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.1516. Min Act: -0.0000

Data Index: 1791231 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 5.7939. Min Range: -5.7939

Max Act: 4.9487. Min Act: -0.0000

Data Index: 1978497 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.6567. Min Act: -0.0000

Data Index: 99471 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.0797. Min Act: -0.0000

Data Index: 404415 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.0658. Min Act: -0.0000

Data Index: 780564 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 5.7939. Min Range: -5.7939

Max Act: 5.0078. Min Act: -0.0000

Data Index: 723674 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 5.7939. Min Range: -5.7939

Max Act: 4.8945. Min Act: -0.0000

Data Index: 951517 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 5.7939. Min Range: -5.7939

Max Act: 4.9230. Min Act: -0.0000

Data Index: 1022682 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 5.7939. Min Range: -5.7939

Max Act: 4.7468. Min Act: -0.0000

Data Index: 1207472 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 5.7939. Min Range: -5.7939

Max Act: 4.9226. Min Act: -0.0000

Data Index: 1100668 (The Pile)

Max Activating Token Index: 251