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

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

Neuron 5357 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.4650. Min Act: -0.0000

Data Index: 518017 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.4125. Min Act: -0.0000

Data Index: 1234986 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.4033. Min Act: -0.0000

Data Index: 881965 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.5146. Min Act: -0.0000

Data Index: 759716 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1178236 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1513140 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1238017 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1628139 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.2227. Min Act: -0.0000

Data Index: 973525 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.1781. Min Act: -0.0000

Data Index: 531066 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.1492. Min Act: -0.0000

Data Index: 880992 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.0938. Min Act: -0.0000

Data Index: 921952 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.5146. Min Range: -1.5146

Max Act: 0.9778. Min Act: -0.0000

Data Index: 457827 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1088087 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.0185. Min Act: -0.0000

Data Index: 202024 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1173223 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.5146. Min Range: -1.5146

Max Act: 1.0436. Min Act: -0.0000

Data Index: 903830 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 1.5146. Min Range: -1.5146

Max Act: 0.9080. Min Act: -0.0000

Data Index: 902018 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.5146. Min Range: -1.5146

Max Act: 0.9932. Min Act: -0.0000

Data Index: 44281 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.5146. Min Range: -1.5146

Max Act: 0.8948. Min Act: -0.0000

Data Index: 931430 (C4 (Web Text))

Max Activating Token Index: 378