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

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

Neuron 4209 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: 1.6636. Min Range: -1.6636

Max Act: 1.6003. Min Act: -0.0000

Data Index: 418132 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.6636. Min Act: -0.0000

Data Index: 611853 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.5630. Min Act: -0.0000

Data Index: 800369 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.5497. Min Act: -0.0000

Data Index: 620607 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.5244. Min Act: 0.0002

Data Index: 913453 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.5286. Min Act: -0.0000

Data Index: 1272265 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.5070. Min Act: -0.0000

Data Index: 27900 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.4103. Min Act: -0.0000

Data Index: 916713 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.4903. Min Act: -0.0000

Data Index: 181684 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.3639. Min Act: -0.0000

Data Index: 459229 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1286778 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.3508. Min Act: -0.0000

Data Index: 708615 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.3515. Min Act: 0.0002

Data Index: 288298 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1050445 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.2453. Min Act: 0.0000

Data Index: 1207092 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.3146. Min Act: -0.0000

Data Index: 831022 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.2900. Min Act: 0.0001

Data Index: 225779 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.2902. Min Act: -0.0000

Data Index: 1038914 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.2700. Min Act: -0.0000

Data Index: 616962 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.6636. Min Range: -1.6636

Max Act: 1.2552. Min Act: 0.0002

Data Index: 1058056 (C4 (Web Text))

Max Activating Token Index: 323