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

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

Neuron 1815 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: 2.0190. Min Range: -2.0190

Max Act: 2.0190. Min Act: -0.0000

Data Index: 1641425 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.9580. Min Act: -0.0000

Data Index: 1632581 (Python Code)

Max Activating Token Index: 950

Text #2

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.8282. Min Act: -0.0000

Data Index: 1502516 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7228. Min Act: -0.0001

Data Index: 1595416 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.8550. Min Act: -0.0000

Data Index: 1365762 (Python Code)

Max Activating Token Index: 132

Text #5

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.8543. Min Act: -0.0001

Data Index: 1558272 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.6391. Min Act: -0.0000

Data Index: 1500705 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.6806. Min Act: -0.0001

Data Index: 1529890 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7962. Min Act: -0.0001

Data Index: 1440622 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7431. Min Act: -0.0001

Data Index: 1463597 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7918. Min Act: -0.0001

Data Index: 1489331 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.6269. Min Act: -0.0000

Data Index: 1363919 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.5405. Min Act: -0.0001

Data Index: 1462573 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7054. Min Act: -0.0000

Data Index: 1426122 (Python Code)

Max Activating Token Index: 603

Text #14

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.6157. Min Act: -0.0001

Data Index: 1480827 (Python Code)

Max Activating Token Index: 813

Text #15

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7185. Min Act: -0.0000

Data Index: 1602594 (Python Code)

Max Activating Token Index: 469

Text #16

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1572449 (Python Code)

Max Activating Token Index: 390

Text #17

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7281. Min Act: -0.0000

Data Index: 1497123 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.7254. Min Act: -0.0001

Data Index: 1527714 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 2.0190. Min Range: -2.0190

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1415330 (Python Code)

Max Activating Token Index: 151