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

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

Neuron 2503 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7307. Min Act: -0.0001

Data Index: 1636668 (Python Code)

Max Activating Token Index: 964

Text #1

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8340. Min Act: -0.0001

Data Index: 1473736 (Python Code)

Max Activating Token Index: 137

Text #2

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8503. Min Act: -0.0001

Data Index: 1387106 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1506596 (Python Code)

Max Activating Token Index: 367

Text #4

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8054. Min Act: -0.0001

Data Index: 1640506 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1434997 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8043. Min Act: -0.0002

Data Index: 1497864 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1620382 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8089. Min Act: -0.0001

Data Index: 1507228 (Python Code)

Max Activating Token Index: 563

Text #9

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7280. Min Act: -0.0001

Data Index: 1554353 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7784. Min Act: -0.0002

Data Index: 1495308 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7467. Min Act: -0.0001

Data Index: 1493466 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7990. Min Act: -0.0001

Data Index: 1515694 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7717. Min Act: -0.0001

Data Index: 1643268 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7899. Min Act: -0.0001

Data Index: 1441772 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7123. Min Act: -0.0001

Data Index: 1511110 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7934. Min Act: -0.0001

Data Index: 1428885 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7289. Min Act: -0.0001

Data Index: 1403751 (Python Code)

Max Activating Token Index: 234

Text #18

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7294. Min Act: -0.0001

Data Index: 1543997 (Python Code)

Max Activating Token Index: 538

Text #19

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1568958 (Python Code)

Max Activating Token Index: 417