Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1601 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3142. Min Act: -0.0002

Data Index: 1517571 (Python Code)

Max Activating Token Index: 604

Text #1

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3201. Min Act: -0.0002

Data Index: 140312 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3046. Min Act: -0.0002

Data Index: 1486075 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1595268 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2932. Min Act: -0.0001

Data Index: 1632669 (Python Code)

Max Activating Token Index: 597

Text #5

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.3109. Min Act: -0.0002

Data Index: 1464302 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2688. Min Act: -0.0001

Data Index: 1065531 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2975. Min Act: -0.0001

Data Index: 1586707 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2877. Min Act: -0.0002

Data Index: 1407986 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1545791 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2813. Min Act: -0.0002

Data Index: 1255147 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2691. Min Act: -0.0001

Data Index: 1451594 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1625015 (Python Code)

Max Activating Token Index: 244

Text #13

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2824. Min Act: -0.0001

Data Index: 691343 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1504103 (Python Code)

Max Activating Token Index: 232

Text #15

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1380641 (Python Code)

Max Activating Token Index: 445

Text #16

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2817. Min Act: -0.0002

Data Index: 1375492 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2624. Min Act: -0.0002

Data Index: 299739 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2854. Min Act: -0.0002

Data Index: 54616 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.3201. Min Range: -0.3201

Max Act: 0.2796. Min Act: -0.0002

Data Index: 1442702 (Python Code)

Max Activating Token Index: 373