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

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

Neuron 1653 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.2045. Min Act: -0.0003

Data Index: 407331 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1971. Min Act: -0.0003

Data Index: 1132412 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1924. Min Act: -0.0002

Data Index: 1177088 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1817. Min Act: -0.0003

Data Index: 577751 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1641. Min Act: -0.0003

Data Index: 509543 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1746. Min Act: -0.0003

Data Index: 468183 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1744. Min Act: -0.0003

Data Index: 307804 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1619. Min Act: -0.0003

Data Index: 410346 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1606. Min Act: -0.0003

Data Index: 660001 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1660. Min Act: -0.0003

Data Index: 626562 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1639. Min Act: -0.0003

Data Index: 570638 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1602. Min Act: -0.0002

Data Index: 1335877 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1600. Min Act: -0.0003

Data Index: 1159646 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1474. Min Act: -0.0002

Data Index: 1259675 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1575. Min Act: -0.0003

Data Index: 751832 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1510. Min Act: -0.0003

Data Index: 715807 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1456. Min Act: -0.0003

Data Index: 681956 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1564. Min Act: -0.0003

Data Index: 994276 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1553. Min Act: -0.0003

Data Index: 225144 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1550. Min Act: -0.0003

Data Index: 284651 (C4 (Web Text))

Max Activating Token Index: 325