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

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

Neuron 3437 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.3945. Min Act: -0.0000

Data Index: 1243210 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.3551. Min Act: -0.0000

Data Index: 823978 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2798. Min Act: -0.0000

Data Index: 199395 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2604. Min Act: -0.0000

Data Index: 951955 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1203508 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2034. Min Act: -0.0000

Data Index: 880094 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1849. Min Act: -0.0000

Data Index: 1294718 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1238. Min Act: -0.0000

Data Index: 280819 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1169. Min Act: -0.0000

Data Index: 204256 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1300. Min Act: -0.0000

Data Index: 176816 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1410. Min Act: -0.0000

Data Index: 406179 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1162. Min Act: -0.0000

Data Index: 879016 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1357176 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0634. Min Act: -0.0000

Data Index: 193140 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1128953 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0920. Min Act: -0.0000

Data Index: 250676 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0827. Min Act: -0.0000

Data Index: 286588 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1093464 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1351700 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0489. Min Act: -0.0000

Data Index: 546517 (C4 (Web Text))

Max Activating Token Index: 385