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

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

Neuron 2854 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.6064. Min Act: -0.0001

Data Index: 1469417 (Python Code)

Max Activating Token Index: 387

Text #1

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.1818. Min Act: -0.0000

Data Index: 1478234 (Python Code)

Max Activating Token Index: 349

Text #2

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.3407. Min Act: -0.0000

Data Index: 1542534 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.4895. Min Act: -0.0000

Data Index: 1587273 (Python Code)

Max Activating Token Index: 522

Text #4

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.4467. Min Act: -0.0000

Data Index: 1409779 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.1826. Min Act: -0.0000

Data Index: 1409818 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.1970. Min Act: -0.0000

Data Index: 1648194 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.4874. Min Act: -0.0000

Data Index: 1569245 (Python Code)

Max Activating Token Index: 267

Text #8

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.1698. Min Act: -0.0000

Data Index: 1364329 (Python Code)

Max Activating Token Index: 389

Text #9

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.3291. Min Act: -0.0000

Data Index: 1592072 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.0079. Min Act: -0.0001

Data Index: 1373190 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.5173. Min Act: -0.0001

Data Index: 1436789 (Python Code)

Max Activating Token Index: 665

Text #12

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.4995. Min Act: -0.0000

Data Index: 1424236 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.3540. Min Act: -0.0000

Data Index: 1571876 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 4.6064. Min Range: -4.6064

Max Act: 3.9958. Min Act: -0.0000

Data Index: 1494604 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.1985. Min Act: -0.0000

Data Index: 1552081 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.3437. Min Act: -0.0000

Data Index: 1488789 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.5128. Min Act: -0.0001

Data Index: 1483458 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.1440. Min Act: -0.0001

Data Index: 1631137 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 4.6064. Min Range: -4.6064

Max Act: 4.2879. Min Act: -0.0000

Data Index: 1655168 (Python Code)

Max Activating Token Index: 116