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

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

Neuron 261 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.2534. Min Act: -0.0000

Data Index: 30548 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1278113 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.2019. Min Act: -0.0000

Data Index: 198512 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.1337. Min Act: -0.0000

Data Index: 625318 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1186617 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0307. Min Act: -0.0000

Data Index: 612477 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0801. Min Act: -0.0000

Data Index: 194811 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0815. Min Act: -0.0000

Data Index: 905110 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0145. Min Act: -0.0000

Data Index: 478778 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9965. Min Act: -0.0000

Data Index: 416518 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0574. Min Act: -0.0000

Data Index: 773215 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9983. Min Act: -0.0000

Data Index: 788241 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1338825 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9546. Min Act: -0.0000

Data Index: 246261 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1142097 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0046. Min Act: -0.0000

Data Index: 40428 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1016568 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0088. Min Act: -0.0000

Data Index: 999048 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1090945 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9739. Min Act: -0.0000

Data Index: 603611 (C4 (Web Text))

Max Activating Token Index: 310