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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4483 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1337410 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1033. Min Act: -0.0000

Data Index: 309300 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1014. Min Act: -0.0000

Data Index: 8188 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1009. Min Act: -0.0000

Data Index: 166958 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0925. Min Act: -0.0000

Data Index: 702580 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0959. Min Act: -0.0000

Data Index: 49070 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1100049 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1226924 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0927. Min Act: -0.0000

Data Index: 995101 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1226352 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0826. Min Act: -0.0000

Data Index: 229694 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0874. Min Act: -0.0000

Data Index: 486313 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0889. Min Act: -0.0000

Data Index: 341038 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0859. Min Act: -0.0000

Data Index: 271525 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0790. Min Act: -0.0000

Data Index: 5091 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0824. Min Act: -0.0000

Data Index: 998824 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0877. Min Act: -0.0000

Data Index: 340844 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0835. Min Act: -0.0000

Data Index: 74900 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0826. Min Act: -0.0000

Data Index: 962415 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1247295 (C4 (Web Text))

Max Activating Token Index: 579