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

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

Neuron 1550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.5995. Min Act: -0.0001

Data Index: 1497987 (Python Code)

Max Activating Token Index: 252

Text #1

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.3018. Min Act: -0.0001

Data Index: 1379145 (Python Code)

Max Activating Token Index: 938

Text #2

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.1216. Min Act: -0.0001

Data Index: 1595808 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.0436. Min Act: -0.0001

Data Index: 1608809 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9172. Min Act: -0.0001

Data Index: 1430385 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 1.5995. Min Range: -1.5995

Max Act: 1.0277. Min Act: -0.0001

Data Index: 1579300 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9548. Min Act: -0.0001

Data Index: 1465570 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9200. Min Act: -0.0001

Data Index: 1376117 (Python Code)

Max Activating Token Index: 950

Text #8

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9614. Min Act: -0.0001

Data Index: 1362387 (Python Code)

Max Activating Token Index: 860

Text #9

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9712. Min Act: -0.0001

Data Index: 1595510 (Python Code)

Max Activating Token Index: 144

Text #10

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9899. Min Act: -0.0001

Data Index: 1619726 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8952. Min Act: -0.0001

Data Index: 1618920 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9933. Min Act: -0.0001

Data Index: 1387754 (Python Code)

Max Activating Token Index: 436

Text #13

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8750. Min Act: -0.0001

Data Index: 1607759 (Python Code)

Max Activating Token Index: 469

Text #14

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9598. Min Act: -0.0001

Data Index: 1487906 (Python Code)

Max Activating Token Index: 1017

Text #15

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9017. Min Act: -0.0001

Data Index: 1600078 (Python Code)

Max Activating Token Index: 467

Text #16

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8868. Min Act: -0.0001

Data Index: 1652244 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9267. Min Act: -0.0001

Data Index: 1408026 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.8330. Min Act: -0.0001

Data Index: 1451881 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 1.5995. Min Range: -1.5995

Max Act: 0.9505. Min Act: -0.0001

Data Index: 1631605 (Python Code)

Max Activating Token Index: 261