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

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

Neuron 44 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0002

Data Index: 867997 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0868. Min Act: -0.0002

Data Index: 130355 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0862. Min Act: -0.0002

Data Index: 469354 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0855. Min Act: -0.0002

Data Index: 677051 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1001840 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0829. Min Act: -0.0002

Data Index: 930094 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0830. Min Act: -0.0002

Data Index: 319488 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0822. Min Act: -0.0002

Data Index: 348243 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0761. Min Act: -0.0002

Data Index: 362876 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0809. Min Act: -0.0002

Data Index: 311709 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1317395 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0811. Min Act: -0.0002

Data Index: 660978 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1026768 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0803. Min Act: -0.0002

Data Index: 864797 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0801. Min Act: -0.0002

Data Index: 26189 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0802. Min Act: -0.0002

Data Index: 104481 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1101607 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0795. Min Act: -0.0002

Data Index: 142802 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0818. Min Act: -0.0002

Data Index: 566830 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0817. Min Act: -0.0002

Data Index: 322480 (C4 (Web Text))

Max Activating Token Index: 308