Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1993 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0003

Data Index: 523970 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0888. Min Act: -0.0003

Data Index: 569705 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0947. Min Act: -0.0003

Data Index: 695457 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0897. Min Act: -0.0004

Data Index: 741290 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0893. Min Act: -0.0003

Data Index: 905373 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0850. Min Act: -0.0003

Data Index: 1145682 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0850. Min Act: -0.0003

Data Index: 534602 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0850. Min Act: -0.0003

Data Index: 633055 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0854. Min Act: -0.0003

Data Index: 783120 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0849. Min Act: -0.0004

Data Index: 295347 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0808. Min Act: -0.0003

Data Index: 692095 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0814. Min Act: -0.0003

Data Index: 755999 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1192141 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0848. Min Act: -0.0003

Data Index: 1056204 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0839. Min Act: -0.0004

Data Index: 853962 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0747. Min Act: -0.0004

Data Index: 11682 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0832. Min Act: -0.0004

Data Index: 122071 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0797. Min Act: -0.0003

Data Index: 1138126 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0794. Min Act: -0.0003

Data Index: 1292353 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0814. Min Act: -0.0003

Data Index: 671096 (C4 (Web Text))

Max Activating Token Index: 716