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

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

Neuron 522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1195983 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1454111 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.5339. Min Act: -0.0000

Data Index: 562365 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1594118 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1196996 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1528267 (Python Code)

Max Activating Token Index: 246

Text #6

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4544. Min Act: -0.0000

Data Index: 269880 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1455507 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1149589 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4446. Min Act: -0.0000

Data Index: 458734 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4747. Min Act: -0.0000

Data Index: 435081 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1530705 (Python Code)

Max Activating Token Index: 622

Text #12

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1423908 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4022. Min Act: -0.0000

Data Index: 113970 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1464041 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1435796 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1487656 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1530229 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1444633 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.5566. Min Range: -0.5566

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1501316 (Python Code)

Max Activating Token Index: 893