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

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

Neuron 792 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4840. Min Range: -1.4840

Max Act: 1.4840. Min Act: -0.0000

Data Index: 953371 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.4840. Min Range: -1.4840

Max Act: 1.1500. Min Act: -0.0000

Data Index: 631104 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.4840. Min Range: -1.4840

Max Act: 1.1010. Min Act: -0.0000

Data Index: 537963 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.4840. Min Range: -1.4840

Max Act: 1.0187. Min Act: -0.0000

Data Index: 479334 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 1.4840. Min Range: -1.4840

Max Act: 1.0134. Min Act: -0.0000

Data Index: 158338 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.4840. Min Range: -1.4840

Max Act: 1.0100. Min Act: -0.0000

Data Index: 973264 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1223318 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.9285. Min Act: -0.0000

Data Index: 657986 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.9174. Min Act: -0.0000

Data Index: 822039 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.9105. Min Act: -0.0000

Data Index: 335765 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1592053 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8247. Min Act: -0.0000

Data Index: 681639 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8594. Min Act: -0.0000

Data Index: 430459 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8079. Min Act: -0.0000

Data Index: 266688 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1345910 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8473. Min Act: -0.0000

Data Index: 905514 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8155. Min Act: -0.0000

Data Index: 668749 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8291. Min Act: -0.0000

Data Index: 515926 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.8300. Min Act: -0.0000

Data Index: 799232 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 1.4840. Min Range: -1.4840

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1296156 (C4 (Web Text))

Max Activating Token Index: 296