Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2564 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0107. Min Range: -1.0107

Max Act: 1.0107. Min Act: -0.0001

Data Index: 377130 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1228208 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7787. Min Act: -0.0002

Data Index: 706546 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8488. Min Act: -0.0002

Data Index: 599520 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8299. Min Act: -0.0001

Data Index: 62302 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7542. Min Act: -0.0001

Data Index: 177628 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8134. Min Act: -0.0002

Data Index: 1233757 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7355. Min Act: -0.0002

Data Index: 1030248 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7279. Min Act: -0.0001

Data Index: 607291 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8307. Min Act: -0.0002

Data Index: 799974 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7114. Min Act: -0.0001

Data Index: 1053097 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7299. Min Act: -0.0001

Data Index: 686651 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7454. Min Act: -0.0001

Data Index: 1316849 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1114662 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8090. Min Act: -0.0001

Data Index: 1046339 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6874. Min Act: -0.0001

Data Index: 345460 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7117. Min Act: -0.0001

Data Index: 683626 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7886. Min Act: -0.0002

Data Index: 463448 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6758. Min Act: -0.0002

Data Index: 1216478 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6744. Min Act: -0.0002

Data Index: 408222 (C4 (Web Text))

Max Activating Token Index: 194