Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 713 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1849. Min Act: -0.0001

Data Index: 428112 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1870. Min Act: -0.0001

Data Index: 141729 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1549. Min Act: -0.0001

Data Index: 982461 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1546. Min Act: -0.0001

Data Index: 819525 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1068287 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1504. Min Act: -0.0001

Data Index: 263270 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1442. Min Act: -0.0001

Data Index: 791253 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1197461 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1456. Min Act: -0.0001

Data Index: 18993 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1438. Min Act: -0.0001

Data Index: 392234 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1422. Min Act: -0.0001

Data Index: 284380 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1412. Min Act: -0.0001

Data Index: 555584 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1404. Min Act: -0.0001

Data Index: 779964 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1377. Min Act: -0.0001

Data Index: 365135 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1315. Min Act: -0.0001

Data Index: 449701 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1361. Min Act: -0.0001

Data Index: 157360 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1338. Min Act: -0.0001

Data Index: 406063 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1240900 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1210. Min Act: -0.0001

Data Index: 709565 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.1870. Min Range: -0.1870

Max Act: 0.1278. Min Act: -0.0001

Data Index: 105608 (C4 (Web Text))

Max Activating Token Index: 365