Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3803 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.8173. Min Act: -0.0000

Data Index: 1275740 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.4657. Min Act: -0.0000

Data Index: 520168 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.4983. Min Act: -0.0000

Data Index: 1035460 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.2755. Min Act: -0.0000

Data Index: 1158702 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.1748. Min Act: -0.0000

Data Index: 1029511 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.1137. Min Act: -0.0000

Data Index: 418967 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.0975. Min Act: -0.0000

Data Index: 654901 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.1961. Min Act: -0.0000

Data Index: 1193167 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.2047. Min Act: -0.0000

Data Index: 132281 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.1764. Min Act: -0.0000

Data Index: 994108 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.1692. Min Act: -0.0000

Data Index: 719075 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.1323. Min Act: -0.0000

Data Index: 267501 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.2034. Min Act: -0.0000

Data Index: 1068543 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.0519. Min Act: -0.0000

Data Index: 587846 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.0477. Min Act: -0.0000

Data Index: 1087793 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.8761. Min Act: -0.0000

Data Index: 615870 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.9921. Min Act: -0.0000

Data Index: 917558 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.9862. Min Act: -0.0000

Data Index: 243166 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.9531. Min Act: -0.0000

Data Index: 391776 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.9618. Min Act: -0.0000

Data Index: 1288286 (C4 (Web Text))

Max Activating Token Index: 860