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

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

Neuron 1800 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: 3.7224. Min Range: -3.7224

Max Act: 3.7224. Min Act: -0.0000

Data Index: 355178 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4242. Min Act: -0.0000

Data Index: 695551 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.5640. Min Act: -0.0000

Data Index: 719610 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.0561. Min Act: -0.0000

Data Index: 1236629 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.0599. Min Act: -0.0000

Data Index: 1088060 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.9141. Min Act: -0.0000

Data Index: 790267 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8868. Min Act: -0.0000

Data Index: 33612 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.0207. Min Act: -0.0000

Data Index: 178980 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.0195. Min Act: -0.0000

Data Index: 671833 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.1410. Min Act: -0.0000

Data Index: 711030 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.9050. Min Act: -0.0000

Data Index: 769247 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8877. Min Act: -0.0000

Data Index: 529623 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8964. Min Act: -0.0000

Data Index: 208517 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8951. Min Act: -0.0000

Data Index: 501248 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8670. Min Act: -0.0000

Data Index: 531962 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8664. Min Act: -0.0000

Data Index: 1052523 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8679. Min Act: -0.0000

Data Index: 301187 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8469. Min Act: -0.0000

Data Index: 567894 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8470. Min Act: -0.0000

Data Index: 989557 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 3.7224. Min Range: -3.7224

Max Act: 2.8136. Min Act: -0.0000

Data Index: 204638 (C4 (Web Text))

Max Activating Token Index: 38