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

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

Neuron 799 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.1816. Min Act: -0.0002

Data Index: 953846 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.1310. Min Act: -0.0002

Data Index: 1238911 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.1019. Min Act: -0.0002

Data Index: 732643 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0099. Min Act: -0.0002

Data Index: 246963 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 1.1816. Min Range: -1.1816

Max Act: 1.0015. Min Act: -0.0003

Data Index: 648664 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9857. Min Act: -0.0002

Data Index: 831462 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9270. Min Act: -0.0002

Data Index: 683470 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9305. Min Act: -0.0002

Data Index: 353373 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9313. Min Act: -0.0002

Data Index: 494457 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9148. Min Act: -0.0003

Data Index: 1024754 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9089. Min Act: -0.0002

Data Index: 478192 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9124. Min Act: -0.0002

Data Index: 66424 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9023. Min Act: -0.0002

Data Index: 276872 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9018. Min Act: -0.0002

Data Index: 225674 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9400. Min Act: -0.0002

Data Index: 1115900 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.8947. Min Act: -0.0003

Data Index: 207025 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.9062. Min Act: -0.0003

Data Index: 1179793 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.8822. Min Act: -0.0002

Data Index: 664048 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.8681. Min Act: -0.0002

Data Index: 1009179 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.1816. Min Range: -1.1816

Max Act: 0.8706. Min Act: -0.0002

Data Index: 1090481 (C4 (Web Text))

Max Activating Token Index: 4