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

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

Neuron 1295 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1312. Min Range: -3.1312

Max Act: 3.1312. Min Act: -0.0000

Data Index: 1368438 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.8925. Min Act: -0.0001

Data Index: 1617084 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.6802. Min Act: -0.0001

Data Index: 1563879 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.2109. Min Act: -0.0001

Data Index: 1360223 (Python Code)

Max Activating Token Index: 561

Text #4

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.1812. Min Act: -0.0000

Data Index: 1651454 (Python Code)

Max Activating Token Index: 119

Text #5

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.3644. Min Act: -0.0000

Data Index: 1615681 (Python Code)

Max Activating Token Index: 751

Text #6

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.1869. Min Act: -0.0000

Data Index: 1585955 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.1821. Min Act: -0.0001

Data Index: 1454721 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1544936 (Python Code)

Max Activating Token Index: 540

Text #9

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1619368 (Python Code)

Max Activating Token Index: 667

Text #10

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.2483. Min Act: -0.0000

Data Index: 1629409 (Python Code)

Max Activating Token Index: 706

Text #11

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.0166. Min Act: -0.0001

Data Index: 1500196 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.1298. Min Act: -0.0000

Data Index: 1414402 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.1114. Min Act: -0.0001

Data Index: 1578273 (Python Code)

Max Activating Token Index: 371

Text #14

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.2289. Min Act: -0.0001

Data Index: 1619411 (Python Code)

Max Activating Token Index: 912

Text #15

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.1173. Min Act: -0.0000

Data Index: 1399420 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.0458. Min Act: -0.0000

Data Index: 1610829 (Python Code)

Max Activating Token Index: 751

Text #17

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.0397. Min Act: -0.0001

Data Index: 1559619 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.0346. Min Act: -0.0001

Data Index: 1363791 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 3.1312. Min Range: -3.1312

Max Act: 2.0323. Min Act: -0.0001

Data Index: 1443916 (Python Code)

Max Activating Token Index: 517