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

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

Neuron 2248 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: 1.5325. Min Range: -1.5325

Max Act: 1.4910. Min Act: -0.0001

Data Index: 1120945 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.5026. Min Act: -0.0001

Data Index: 808612 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.5325. Min Act: -0.0001

Data Index: 1272219 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.2211. Min Act: -0.0001

Data Index: 1020711 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.3403. Min Act: -0.0001

Data Index: 1257949 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.2757. Min Act: -0.0001

Data Index: 1086843 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.2910. Min Act: -0.0001

Data Index: 952854 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.2471. Min Act: -0.0001

Data Index: 307323 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.2458. Min Act: -0.0001

Data Index: 876520 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.2039. Min Act: -0.0001

Data Index: 952966 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.1597. Min Act: -0.0001

Data Index: 714821 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.1691. Min Act: -0.0001

Data Index: 883244 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.2645. Min Act: -0.0001

Data Index: 986053 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.1483. Min Act: -0.0001

Data Index: 1126996 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.0977. Min Act: -0.0001

Data Index: 713899 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.0583. Min Act: -0.0001

Data Index: 863364 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.1199. Min Act: -0.0001

Data Index: 980941 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.1467. Min Act: -0.0001

Data Index: 1286569 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.1458. Min Act: -0.0001

Data Index: 1197825 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 1.5325. Min Range: -1.5325

Max Act: 1.0345. Min Act: -0.0001

Data Index: 1083553 (C4 (Web Text))

Max Activating Token Index: 885