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

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

Neuron 3847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.2819. Min Act: -0.0000

Data Index: 1432012 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1493898 (Python Code)

Max Activating Token Index: 609

Text #2

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.3232. Min Act: -0.0000

Data Index: 1493043 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.2388. Min Act: -0.0000

Data Index: 1591820 (Python Code)

Max Activating Token Index: 627

Text #4

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.1913. Min Act: -0.0000

Data Index: 1406825 (Python Code)

Max Activating Token Index: 415

Text #5

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.2088. Min Act: -0.0000

Data Index: 1399436 (Python Code)

Max Activating Token Index: 215

Text #6

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.1026. Min Act: -0.0000

Data Index: 1482040 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.0947. Min Act: -0.0000

Data Index: 1644181 (Python Code)

Max Activating Token Index: 272

Text #8

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.0755. Min Act: -0.0000

Data Index: 1549659 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9835. Min Act: -0.0001

Data Index: 1378505 (Python Code)

Max Activating Token Index: 123

Text #10

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9747. Min Act: -0.0000

Data Index: 1609136 (Python Code)

Max Activating Token Index: 497

Text #11

Max Range: 2.3232. Min Range: -2.3232

Max Act: 2.0566. Min Act: -0.0000

Data Index: 408958 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1613116 (Python Code)

Max Activating Token Index: 863

Text #13

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8512. Min Act: -0.0000

Data Index: 1635952 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.9881. Min Act: -0.0000

Data Index: 1574145 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.8085. Min Act: -0.0000

Data Index: 1557881 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.7720. Min Act: -0.0000

Data Index: 1539810 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.7810. Min Act: -0.0000

Data Index: 1475471 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.7247. Min Act: -0.0000

Data Index: 199415 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 2.3232. Min Range: -2.3232

Max Act: 1.7124. Min Act: -0.0000

Data Index: 1636435 (Python Code)

Max Activating Token Index: 545