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

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

Neuron 3830 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: 2.8044. Min Range: -2.8044

Max Act: 2.8044. Min Act: -0.0000

Data Index: 1534331 (Python Code)

Max Activating Token Index: 732

Text #1

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.5665. Min Act: -0.0000

Data Index: 1623799 (Python Code)

Max Activating Token Index: 972

Text #2

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.4641. Min Act: -0.0000

Data Index: 1642532 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.4331. Min Act: -0.0000

Data Index: 1488695 (Python Code)

Max Activating Token Index: 895

Text #4

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.2058. Min Act: -0.0000

Data Index: 1627094 (Python Code)

Max Activating Token Index: 468

Text #5

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.3168. Min Act: -0.0000

Data Index: 1391821 (Python Code)

Max Activating Token Index: 548

Text #6

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.0395. Min Act: -0.0000

Data Index: 1574383 (Python Code)

Max Activating Token Index: 585

Text #7

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.2237. Min Act: -0.0000

Data Index: 1572981 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.1322. Min Act: -0.0000

Data Index: 1612568 (Python Code)

Max Activating Token Index: 487

Text #9

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.2345. Min Act: -0.0000

Data Index: 1529662 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.1092. Min Act: -0.0000

Data Index: 1453844 (Python Code)

Max Activating Token Index: 792

Text #11

Max Range: 2.8044. Min Range: -2.8044

Max Act: 1.8578. Min Act: -0.0000

Data Index: 1490746 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 2.8044. Min Range: -2.8044

Max Act: 1.8352. Min Act: -0.0000

Data Index: 1364379 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.1305. Min Act: -0.0000

Data Index: 1579136 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.0887. Min Act: -0.0000

Data Index: 1654756 (Python Code)

Max Activating Token Index: 821

Text #15

Max Range: 2.8044. Min Range: -2.8044

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1462815 (Python Code)

Max Activating Token Index: 800

Text #16

Max Range: 2.8044. Min Range: -2.8044

Max Act: 1.8620. Min Act: -0.0000

Data Index: 1503105 (Python Code)

Max Activating Token Index: 970

Text #17

Max Range: 2.8044. Min Range: -2.8044

Max Act: 2.0405. Min Act: -0.0000

Data Index: 1634240 (Python Code)

Max Activating Token Index: 470

Text #18

Max Range: 2.8044. Min Range: -2.8044

Max Act: 1.7208. Min Act: -0.0000

Data Index: 1575667 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 2.8044. Min Range: -2.8044

Max Act: 1.9241. Min Act: -0.0000

Data Index: 1435092 (Python Code)

Max Activating Token Index: 378