Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 568 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0958. Min Act: -0.0003

Data Index: 1101054 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0003

Data Index: 233063 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0899. Min Act: -0.0003

Data Index: 714528 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0851. Min Act: -0.0003

Data Index: 103187 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1049561 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0814. Min Act: -0.0003

Data Index: 815846 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1319556 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0759. Min Act: -0.0003

Data Index: 1359028 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0662. Min Act: -0.0003

Data Index: 475557 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0761. Min Act: -0.0003

Data Index: 285893 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0706. Min Act: -0.0003

Data Index: 503247 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0693. Min Act: -0.0003

Data Index: 15626 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0727. Min Act: -0.0003

Data Index: 973595 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0719. Min Act: -0.0003

Data Index: 512712 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1295321 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0712. Min Act: -0.0003

Data Index: 540645 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0686. Min Act: -0.0003

Data Index: 382776 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1114181 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1308617 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0635. Min Act: -0.0003

Data Index: 598003 (C4 (Web Text))

Max Activating Token Index: 1011