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

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

Neuron 1046 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: 1.3518. Min Range: -1.3518

Max Act: 1.3399. Min Act: -0.0001

Data Index: 876606 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.3518. Min Act: -0.0001

Data Index: 1083024 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.2791. Min Act: -0.0001

Data Index: 1007772 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.2759. Min Act: -0.0001

Data Index: 207942 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.2739. Min Act: -0.0001

Data Index: 495549 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.3109. Min Act: -0.0001

Data Index: 375034 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.1752. Min Act: -0.0001

Data Index: 800873 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.3021. Min Act: -0.0001

Data Index: 705446 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.2533. Min Act: -0.0001

Data Index: 365761 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.0779. Min Act: -0.0001

Data Index: 443797 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.1589. Min Act: -0.0001

Data Index: 234853 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.3261. Min Act: -0.0001

Data Index: 690037 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.1370. Min Act: -0.0001

Data Index: 231906 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.1902. Min Act: -0.0001

Data Index: 1215396 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.1070. Min Act: -0.0001

Data Index: 249088 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.1283. Min Act: -0.0001

Data Index: 944218 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.0345. Min Act: -0.0001

Data Index: 54083 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.1309. Min Act: -0.0001

Data Index: 571312 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.0202. Min Act: -0.0001

Data Index: 885938 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 1.3518. Min Range: -1.3518

Max Act: 1.1251. Min Act: -0.0001

Data Index: 1142148 (C4 (Web Text))

Max Activating Token Index: 855