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

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

Neuron 5738 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8698. Min Range: -2.8698

Max Act: 2.8698. Min Act: -0.0000

Data Index: 1626335 (Python Code)

Max Activating Token Index: 973

Text #1

Max Range: 2.8698. Min Range: -2.8698

Max Act: 2.3523. Min Act: -0.0000

Data Index: 1377590 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 2.8698. Min Range: -2.8698

Max Act: 2.3638. Min Act: -0.0000

Data Index: 1523132 (Python Code)

Max Activating Token Index: 81

Text #3

Max Range: 2.8698. Min Range: -2.8698

Max Act: 2.3868. Min Act: -0.0000

Data Index: 1466765 (Python Code)

Max Activating Token Index: 818

Text #4

Max Range: 2.8698. Min Range: -2.8698

Max Act: 2.2272. Min Act: -0.0000

Data Index: 1508637 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 2.8698. Min Range: -2.8698

Max Act: 2.3258. Min Act: -0.0000

Data Index: 1387792 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 2.8698. Min Range: -2.8698

Max Act: 2.1919. Min Act: -0.0000

Data Index: 1395485 (Python Code)

Max Activating Token Index: 307

Text #7

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.8587. Min Act: -0.0000

Data Index: 1573023 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.9624. Min Act: -0.0000

Data Index: 1519859 (Python Code)

Max Activating Token Index: 133

Text #9

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1476801 (Python Code)

Max Activating Token Index: 947

Text #10

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1502335 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.9182. Min Act: -0.0000

Data Index: 1571229 (Python Code)

Max Activating Token Index: 429

Text #12

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.8528. Min Act: -0.0000

Data Index: 1624465 (Python Code)

Max Activating Token Index: 896

Text #13

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.9374. Min Act: -0.0000

Data Index: 1361695 (Python Code)

Max Activating Token Index: 913

Text #14

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.7372. Min Act: -0.0000

Data Index: 1471979 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.8210. Min Act: -0.0000

Data Index: 1575346 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1586609 (Python Code)

Max Activating Token Index: 93

Text #17

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.7175. Min Act: -0.0000

Data Index: 1625764 (Python Code)

Max Activating Token Index: 873

Text #18

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1538952 (Python Code)

Max Activating Token Index: 240

Text #19

Max Range: 2.8698. Min Range: -2.8698

Max Act: 1.6903. Min Act: -0.0000

Data Index: 1476917 (Python Code)

Max Activating Token Index: 293