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

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

Neuron 2988 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1103320 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1563. Min Act: -0.0000

Data Index: 721913 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1192395 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1577. Min Act: -0.0000

Data Index: 465755 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1543. Min Act: -0.0001

Data Index: 1087238 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1498. Min Act: -0.0001

Data Index: 893638 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1401. Min Act: -0.0000

Data Index: 194534 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1459. Min Act: -0.0001

Data Index: 902176 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1090031 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1367. Min Act: -0.0001

Data Index: 773076 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1307. Min Act: -0.0000

Data Index: 378399 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1406. Min Act: -0.0001

Data Index: 333261 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1340. Min Act: -0.0000

Data Index: 219656 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1395. Min Act: -0.0000

Data Index: 498250 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1330. Min Act: -0.0000

Data Index: 268122 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1289. Min Act: -0.0000

Data Index: 107116 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1374. Min Act: -0.0000

Data Index: 589847 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1331. Min Act: -0.0001

Data Index: 901775 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1342. Min Act: -0.0001

Data Index: 909235 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1323. Min Act: -0.0001

Data Index: 230437 (C4 (Web Text))

Max Activating Token Index: 123