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

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

Neuron 37 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1483. Min Act: -0.0001

Data Index: 604173 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1481. Min Act: -0.0001

Data Index: 715815 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1474. Min Act: -0.0001

Data Index: 289001 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1325178 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1159118 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1118859 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1415. Min Act: -0.0001

Data Index: 266036 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1401. Min Act: -0.0001

Data Index: 919066 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1320. Min Act: -0.0001

Data Index: 670499 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1041607 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1190158 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1398. Min Act: -0.0001

Data Index: 271271 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1325281 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1381. Min Act: -0.0001

Data Index: 924890 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1433. Min Act: -0.0001

Data Index: 400789 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1370. Min Act: -0.0001

Data Index: 75821 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1415. Min Act: -0.0001

Data Index: 617859 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1414. Min Act: -0.0001

Data Index: 664748 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1358. Min Act: -0.0001

Data Index: 772920 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.1483. Min Range: -0.1483

Max Act: 0.1353. Min Act: -0.0001

Data Index: 790285 (C4 (Web Text))

Max Activating Token Index: 189