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

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

Neuron 4335 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8053. Min Range: -5.8053

Max Act: 5.8053. Min Act: -0.0001

Data Index: 1096782 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.4603. Min Act: -0.0000

Data Index: 376833 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.3680. Min Act: -0.0001

Data Index: 399725 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.1721. Min Act: -0.0001

Data Index: 1357309 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 5.8053. Min Range: -5.8053

Max Act: 4.0261. Min Act: -0.0001

Data Index: 57776 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.9344. Min Act: -0.0001

Data Index: 688719 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.7048. Min Act: -0.0001

Data Index: 117462 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.6550. Min Act: -0.0000

Data Index: 689284 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.4752. Min Act: -0.0000

Data Index: 268247 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.2679. Min Act: -0.0001

Data Index: 235172 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.3675. Min Act: -0.0001

Data Index: 335516 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.4914. Min Act: -0.0000

Data Index: 313002 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.2791. Min Act: -0.0001

Data Index: 1126538 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 5.8053. Min Range: -5.8053

Max Act: 2.8128. Min Act: -0.0000

Data Index: 1035373 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.2133. Min Act: -0.0000

Data Index: 824594 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.3385. Min Act: -0.0001

Data Index: 517158 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.2080. Min Act: -0.0001

Data Index: 242894 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.3080. Min Act: -0.0000

Data Index: 1133498 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 5.8053. Min Range: -5.8053

Max Act: 2.7094. Min Act: -0.0001

Data Index: 697747 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 5.8053. Min Range: -5.8053

Max Act: 3.1238. Min Act: -0.0000

Data Index: 1235043 (C4 (Web Text))

Max Activating Token Index: 566