Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 654 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0072. Min Range: -2.0072

Max Act: 2.0072. Min Act: -0.0001

Data Index: 1396994 (Python Code)

Max Activating Token Index: 480

Text #1

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.7794. Min Act: -0.0001

Data Index: 38816 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.5863. Min Act: -0.0001

Data Index: 63594 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.4741. Min Act: -0.0000

Data Index: 1007942 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1246728 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1130585 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1031675 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1712. Min Act: -0.0001

Data Index: 1170685 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2470. Min Act: -0.0001

Data Index: 1554439 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2799. Min Act: -0.0000

Data Index: 706016 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2566. Min Act: -0.0001

Data Index: 1641562 (Python Code)

Max Activating Token Index: 524

Text #11

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1028. Min Act: -0.0000

Data Index: 362874 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2391. Min Act: -0.0000

Data Index: 1446464 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1589089 (Python Code)

Max Activating Token Index: 689

Text #14

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1602018 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1271304 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2460. Min Act: -0.0000

Data Index: 1364580 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1645721 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.2033. Min Act: -0.0001

Data Index: 1497812 (Python Code)

Max Activating Token Index: 213

Text #19

Max Range: 2.0072. Min Range: -2.0072

Max Act: 1.1095. Min Act: -0.0001

Data Index: 91037 (C4 (Web Text))

Max Activating Token Index: 878