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

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

Neuron 1592 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.8189. Min Act: -0.0000

Data Index: 1599473 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.6664. Min Act: 0.0000

Data Index: 1513774 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.6230. Min Act: 0.0000

Data Index: 1568355 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.5518. Min Act: -0.0000

Data Index: 1491141 (Python Code)

Max Activating Token Index: 641

Text #4

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.4889. Min Act: 0.0000

Data Index: 1477460 (Python Code)

Max Activating Token Index: 417

Text #5

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1468449 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.6507. Min Act: -0.0000

Data Index: 1596849 (Python Code)

Max Activating Token Index: 1007

Text #7

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.4509. Min Act: -0.0000

Data Index: 1533924 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3384. Min Act: 0.0000

Data Index: 1599268 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3301. Min Act: 0.0000

Data Index: 1558282 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1387724 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.2384. Min Act: 0.0000

Data Index: 1414555 (Python Code)

Max Activating Token Index: 446

Text #12

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1397106 (Python Code)

Max Activating Token Index: 122

Text #13

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3411. Min Act: 0.0000

Data Index: 1571735 (Python Code)

Max Activating Token Index: 221

Text #14

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1364245 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1581361 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3636. Min Act: 0.0000

Data Index: 1473098 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1530902 (Python Code)

Max Activating Token Index: 298

Text #18

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1362108 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1607033 (Python Code)

Max Activating Token Index: 423