Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2820 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3315. Min Act: -0.0003

Data Index: 1030060 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3691. Min Act: -0.0003

Data Index: 73996 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3224. Min Act: -0.0003

Data Index: 296615 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2906. Min Act: -0.0003

Data Index: 137642 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2961. Min Act: -0.0003

Data Index: 847889 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3081. Min Act: -0.0003

Data Index: 355411 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2909. Min Act: -0.0003

Data Index: 59003 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3194. Min Act: -0.0003

Data Index: 457248 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2778. Min Act: -0.0003

Data Index: 1038570 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2711. Min Act: -0.0003

Data Index: 568296 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2574. Min Act: -0.0003

Data Index: 135449 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2864. Min Act: -0.0003

Data Index: 512645 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2964. Min Act: -0.0003

Data Index: 1357405 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2817. Min Act: -0.0003

Data Index: 550279 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2590. Min Act: -0.0003

Data Index: 335258 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2452. Min Act: -0.0003

Data Index: 11990 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2461. Min Act: -0.0003

Data Index: 60843 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2643. Min Act: -0.0003

Data Index: 450310 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2749. Min Act: -0.0003

Data Index: 684434 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2561. Min Act: -0.0003

Data Index: 189628 (C4 (Web Text))

Max Activating Token Index: 740