Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3945 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.2010. Min Act: -0.0000

Data Index: 262519 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1145755 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1605. Min Act: -0.0000

Data Index: 733851 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1491. Min Act: -0.0000

Data Index: 674944 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1488. Min Act: -0.0000

Data Index: 93595 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1435. Min Act: -0.0000

Data Index: 334482 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1440. Min Act: -0.0000

Data Index: 608591 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1529. Min Act: -0.0000

Data Index: 454967 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1457. Min Act: -0.0000

Data Index: 437739 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1493. Min Act: -0.0000

Data Index: 426830 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1448. Min Act: -0.0000

Data Index: 277603 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1375. Min Act: -0.0000

Data Index: 526044 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1420. Min Act: -0.0000

Data Index: 908804 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1381. Min Act: -0.0000

Data Index: 570319 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1328. Min Act: -0.0000

Data Index: 928000 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1355360 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1366. Min Act: -0.0000

Data Index: 467996 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1352. Min Act: -0.0000

Data Index: 499616 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1248558 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1343. Min Act: -0.0000

Data Index: 896281 (C4 (Web Text))

Max Activating Token Index: 666