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

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

Neuron 516 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.8385. Min Act: -0.0000

Data Index: 1380829 (Python Code)

Max Activating Token Index: 330

Text #1

Max Range: 4.0276. Min Range: -4.0276

Max Act: 4.0276. Min Act: -0.0000

Data Index: 1604825 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.9175. Min Act: -0.0000

Data Index: 1496517 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.5893. Min Act: -0.0000

Data Index: 1387495 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.7308. Min Act: -0.0000

Data Index: 1549036 (Python Code)

Max Activating Token Index: 359

Text #5

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.5818. Min Act: -0.0000

Data Index: 1567301 (Python Code)

Max Activating Token Index: 926

Text #6

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.5821. Min Act: -0.0000

Data Index: 1393186 (Python Code)

Max Activating Token Index: 723

Text #7

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.5517. Min Act: -0.0000

Data Index: 1587156 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.5173. Min Act: -0.0000

Data Index: 1522514 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.4636. Min Act: -0.0000

Data Index: 1436273 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.2825. Min Act: -0.0000

Data Index: 1451411 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.3527. Min Act: -0.0000

Data Index: 1404274 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.4884. Min Act: -0.0000

Data Index: 1613880 (Python Code)

Max Activating Token Index: 151

Text #13

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.1669. Min Act: -0.0000

Data Index: 1624856 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.4329. Min Act: -0.0000

Data Index: 1471155 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.1154. Min Act: -0.0000

Data Index: 1440519 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.2098. Min Act: -0.0000

Data Index: 1628151 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.0188. Min Act: -0.0000

Data Index: 1366724 (Python Code)

Max Activating Token Index: 298

Text #18

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.1746. Min Act: -0.0000

Data Index: 1535522 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 4.0276. Min Range: -4.0276

Max Act: 3.1224. Min Act: -0.0000

Data Index: 1543951 (Python Code)

Max Activating Token Index: 147