Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2814 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.5639. Min Act: -0.0000

Data Index: 143257 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1083347 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.5082. Min Act: -0.0000

Data Index: 102335 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4648. Min Act: -0.0000

Data Index: 948114 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4880. Min Act: -0.0000

Data Index: 329949 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4571. Min Act: -0.0000

Data Index: 908636 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4731. Min Act: -0.0000

Data Index: 27071 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4515. Min Act: -0.0000

Data Index: 62868 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4349. Min Act: -0.0000

Data Index: 6957 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1074907 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4209. Min Act: -0.0000

Data Index: 269888 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4477. Min Act: -0.0000

Data Index: 803101 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4285. Min Act: -0.0000

Data Index: 98764 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4050. Min Act: -0.0000

Data Index: 836455 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1182046 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4310. Min Act: -0.0000

Data Index: 971182 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1217339 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4158. Min Act: -0.0000

Data Index: 638897 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.3996. Min Act: -0.0000

Data Index: 812579 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4162. Min Act: -0.0000

Data Index: 169531 (C4 (Web Text))

Max Activating Token Index: 802