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

Dataset: The Pile

Neuron 2380 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: 4.0921. Min Range: -4.0921

Max Act: 4.0921. Min Act: -0.0000

Data Index: 131381 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.7650. Min Act: -0.0000

Data Index: 121641 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.8749. Min Act: -0.0000

Data Index: 530504 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 4.0921. Min Range: -4.0921

Max Act: 4.0772. Min Act: -0.0000

Data Index: 824591 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.6289. Min Act: -0.0000

Data Index: 418941 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.2222. Min Act: -0.0000

Data Index: 1516647 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.1311. Min Act: -0.0000

Data Index: 723646 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.5424. Min Act: -0.0000

Data Index: 167792 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.3870. Min Act: 0.0000

Data Index: 21735 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.1588. Min Act: -0.0000

Data Index: 1748955 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.1369. Min Act: -0.0000

Data Index: 1053827 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.2425. Min Act: -0.0000

Data Index: 1040115 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.8013. Min Act: -0.0000

Data Index: 1892469 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.1791. Min Act: -0.0000

Data Index: 1427689 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.3893. Min Act: -0.0000

Data Index: 464660 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.1043. Min Act: -0.0000

Data Index: 1571261 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.2462. Min Act: -0.0000

Data Index: 758650 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.5311. Min Act: -0.0000

Data Index: 1053005 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.2264. Min Act: -0.0000

Data Index: 414550 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.2264. Min Act: -0.0000

Data Index: 469452 (The Pile)

Max Activating Token Index: 978