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

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

Neuron 5805 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.6181. Min Act: -0.0002

Data Index: 239402 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5861. Min Act: -0.0002

Data Index: 866960 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5279. Min Act: -0.0002

Data Index: 1298173 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5217. Min Act: -0.0002

Data Index: 151390 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5367. Min Act: -0.0002

Data Index: 1526810 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4826. Min Act: -0.0002

Data Index: 1432563 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5444. Min Act: -0.0002

Data Index: 681933 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4747. Min Act: -0.0002

Data Index: 1551463 (Python Code)

Max Activating Token Index: 868

Text #8

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5080. Min Act: -0.0002

Data Index: 1386881 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4909. Min Act: -0.0002

Data Index: 1393719 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4871. Min Act: -0.0002

Data Index: 1388241 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4858. Min Act: -0.0002

Data Index: 1552604 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5011. Min Act: -0.0001

Data Index: 1423103 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4527. Min Act: -0.0002

Data Index: 1572063 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4855. Min Act: -0.0002

Data Index: 1427784 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4645. Min Act: -0.0002

Data Index: 1426217 (Python Code)

Max Activating Token Index: 926

Text #16

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4578. Min Act: -0.0002

Data Index: 1501194 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4541. Min Act: -0.0002

Data Index: 1482200 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4513. Min Act: -0.0002

Data Index: 1511042 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.4460. Min Act: -0.0002

Data Index: 1577045 (Python Code)

Max Activating Token Index: 612