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

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

Neuron 3809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3289. Min Range: -4.3289

Max Act: 4.3289. Min Act: -0.0000

Data Index: 1565249 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.7593. Min Act: -0.0001

Data Index: 1541448 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.7856. Min Act: -0.0000

Data Index: 1413470 (Python Code)

Max Activating Token Index: 555

Text #3

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.6056. Min Act: -0.0001

Data Index: 1579875 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.5942. Min Act: -0.0001

Data Index: 1587084 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.4238. Min Act: -0.0000

Data Index: 1504838 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.4296. Min Act: -0.0000

Data Index: 1541365 (Python Code)

Max Activating Token Index: 938

Text #7

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.5415. Min Act: -0.0000

Data Index: 1606001 (Python Code)

Max Activating Token Index: 482

Text #8

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.3236. Min Act: -0.0001

Data Index: 1529164 (Python Code)

Max Activating Token Index: 538

Text #9

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.1741. Min Act: -0.0000

Data Index: 1612071 (Python Code)

Max Activating Token Index: 934

Text #10

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.1384. Min Act: -0.0001

Data Index: 1573486 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.4325. Min Act: -0.0000

Data Index: 1457187 (Python Code)

Max Activating Token Index: 754

Text #12

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.3532. Min Act: -0.0000

Data Index: 1438753 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.3434. Min Act: -0.0000

Data Index: 1625783 (Python Code)

Max Activating Token Index: 767

Text #14

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.1896. Min Act: -0.0000

Data Index: 1481675 (Python Code)

Max Activating Token Index: 746

Text #15

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.1689. Min Act: -0.0000

Data Index: 1559849 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.3211. Min Act: -0.0000

Data Index: 1598180 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.4595. Min Act: -0.0000

Data Index: 1436389 (Python Code)

Max Activating Token Index: 671

Text #18

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.3031. Min Act: -0.0000

Data Index: 1503511 (Python Code)

Max Activating Token Index: 772

Text #19

Max Range: 4.3289. Min Range: -4.3289

Max Act: 3.2872. Min Act: -0.0000

Data Index: 1449745 (Python Code)

Max Activating Token Index: 917