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

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

Neuron 1758 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.7218. Min Act: -0.0000

Data Index: 1172727 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.0753. Min Act: -0.0000

Data Index: 433241 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8953. Min Act: -0.0000

Data Index: 749234 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.9389. Min Act: -0.0000

Data Index: 682034 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.0091. Min Act: -0.0000

Data Index: 905832 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.9267. Min Act: -0.0000

Data Index: 625113 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.9616. Min Act: -0.0000

Data Index: 491008 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.9775. Min Act: -0.0000

Data Index: 800619 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.9348. Min Act: -0.0000

Data Index: 241276 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8716. Min Act: -0.0000

Data Index: 258203 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1119963 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.7890. Min Act: -0.0000

Data Index: 359458 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8807. Min Act: -0.0000

Data Index: 684168 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8739. Min Act: -0.0000

Data Index: 351173 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8936. Min Act: -0.0000

Data Index: 355183 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1218007 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8758. Min Act: -0.0000

Data Index: 556721 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1164101 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1321674 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8424. Min Act: -0.0000

Data Index: 54613 (C4 (Web Text))

Max Activating Token Index: 889