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

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

Neuron 2143 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2165. Min Act: -0.0001

Data Index: 768353 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2252. Min Act: -0.0001

Data Index: 464836 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1972. Min Act: -0.0001

Data Index: 826353 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1117823 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1992. Min Act: -0.0001

Data Index: 765657 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2092. Min Act: -0.0001

Data Index: 200275 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1758. Min Act: -0.0001

Data Index: 337616 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1777. Min Act: -0.0001

Data Index: 152264 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1873. Min Act: -0.0001

Data Index: 699848 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1840. Min Act: -0.0001

Data Index: 93138 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1682. Min Act: -0.0001

Data Index: 688652 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1765. Min Act: -0.0001

Data Index: 199893 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1832. Min Act: -0.0001

Data Index: 1317301 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1784. Min Act: -0.0001

Data Index: 104196 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1767. Min Act: -0.0001

Data Index: 474735 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1689. Min Act: -0.0001

Data Index: 649862 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1699. Min Act: -0.0001

Data Index: 89184 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1658. Min Act: -0.0001

Data Index: 268254 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1540. Min Act: -0.0001

Data Index: 802613 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1606. Min Act: -0.0001

Data Index: 272744 (C4 (Web Text))

Max Activating Token Index: 509