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

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

Neuron 2854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3905. Min Act: -0.0001

Data Index: 1460763 (Python Code)

Max Activating Token Index: 194

Text #1

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.5630. Min Act: -0.0001

Data Index: 1368379 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.5419. Min Act: -0.0001

Data Index: 558440 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.4571. Min Act: -0.0001

Data Index: 1458726 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1170944 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3723. Min Act: -0.0001

Data Index: 1535954 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3326. Min Act: -0.0001

Data Index: 755137 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.4534. Min Act: -0.0001

Data Index: 1597296 (Python Code)

Max Activating Token Index: 957

Text #8

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3526. Min Act: -0.0001

Data Index: 1506997 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3568. Min Act: -0.0001

Data Index: 1627379 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2149. Min Act: -0.0001

Data Index: 1390297 (Python Code)

Max Activating Token Index: 550

Text #11

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.1400. Min Act: -0.0001

Data Index: 1456369 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2679. Min Act: -0.0001

Data Index: 1361024 (Python Code)

Max Activating Token Index: 592

Text #13

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2600. Min Act: -0.0000

Data Index: 19111 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2462. Min Act: -0.0000

Data Index: 878534 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.1968. Min Act: -0.0001

Data Index: 1635649 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2226. Min Act: -0.0001

Data Index: 739590 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.1845. Min Act: -0.0001

Data Index: 1423215 (Python Code)

Max Activating Token Index: 999

Text #18

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.0714. Min Act: -0.0001

Data Index: 381048 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.1655. Min Act: -0.0000

Data Index: 290612 (C4 (Web Text))

Max Activating Token Index: 296