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

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

Neuron 1056 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: 2.8819. Min Range: -2.8819

Max Act: 2.8819. Min Act: -0.0000

Data Index: 419525 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.6661. Min Act: -0.0000

Data Index: 850314 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.6042. Min Act: -0.0000

Data Index: 1255335 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.8241. Min Act: -0.0000

Data Index: 1142110 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.6086. Min Act: -0.0000

Data Index: 407602 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.6889. Min Act: -0.0000

Data Index: 210133 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.6928. Min Act: -0.0000

Data Index: 672630 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.5871. Min Act: -0.0000

Data Index: 977782 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.6714. Min Act: -0.0000

Data Index: 984218 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.4774. Min Act: -0.0000

Data Index: 146890 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.4490. Min Act: -0.0000

Data Index: 1133038 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.1164. Min Act: -0.0000

Data Index: 335606 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.3327. Min Act: -0.0000

Data Index: 567983 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.3147. Min Act: -0.0000

Data Index: 631419 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.2941. Min Act: -0.0000

Data Index: 181855 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.2255. Min Act: -0.0000

Data Index: 918568 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.2764. Min Act: -0.0000

Data Index: 268123 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.0208. Min Act: -0.0000

Data Index: 328065 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.2418. Min Act: -0.0000

Data Index: 550784 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 2.8819. Min Range: -2.8819

Max Act: 2.1022. Min Act: -0.0000

Data Index: 696222 (C4 (Web Text))

Max Activating Token Index: 384