Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1186 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1391447 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1548511 (Python Code)

Max Activating Token Index: 798

Text #2

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1550161 (Python Code)

Max Activating Token Index: 348

Text #3

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1368040 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1382356 (Python Code)

Max Activating Token Index: 314

Text #5

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1472749 (Python Code)

Max Activating Token Index: 456

Text #6

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1558545 (Python Code)

Max Activating Token Index: 234

Text #7

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1380497 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2614. Min Act: 0.0001

Data Index: 1524163 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1454433 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1445212 (Python Code)

Max Activating Token Index: 708

Text #11

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1546795 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1560793 (Python Code)

Max Activating Token Index: 170

Text #13

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1631199 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1403167 (Python Code)

Max Activating Token Index: 900

Text #15

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1612641 (Python Code)

Max Activating Token Index: 82

Text #16

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1481692 (Python Code)

Max Activating Token Index: 92

Text #17

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1482667 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1465415 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 0.2681. Min Range: -0.2681

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1461645 (Python Code)

Max Activating Token Index: 139