Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1203 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0003

Data Index: 256800 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0741. Min Act: -0.0003

Data Index: 899333 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0646. Min Act: -0.0003

Data Index: 157977 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1065851 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0553. Min Act: -0.0003

Data Index: 931301 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0562. Min Act: -0.0004

Data Index: 591147 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0525. Min Act: -0.0003

Data Index: 775361 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0545. Min Act: -0.0003

Data Index: 735099 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0528. Min Act: -0.0003

Data Index: 868712 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1584241 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1386354 (Python Code)

Max Activating Token Index: 887

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1620592 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1013922 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0518. Min Act: -0.0003

Data Index: 644845 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1495832 (Python Code)

Max Activating Token Index: 776

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0487. Min Act: -0.0003

Data Index: 798423 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1374657 (Python Code)

Max Activating Token Index: 612

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0460. Min Act: -0.0003

Data Index: 491660 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1387589 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0479. Min Act: -0.0003

Data Index: 497604 (C4 (Web Text))

Max Activating Token Index: 951