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

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

Neuron 4117 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2782. Min Range: -1.2782

Max Act: 1.2782. Min Act: -0.0000

Data Index: 849711 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.2782. Min Range: -1.2782

Max Act: 1.1724. Min Act: -0.0000

Data Index: 392041 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.2782. Min Range: -1.2782

Max Act: 1.0678. Min Act: -0.0000

Data Index: 331020 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.9623. Min Act: -0.0000

Data Index: 108571 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.2782. Min Range: -1.2782

Max Act: 1.0404. Min Act: -0.0000

Data Index: 52439 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.8780. Min Act: -0.0000

Data Index: 488556 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.8948. Min Act: -0.0000

Data Index: 344427 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.9207. Min Act: -0.0000

Data Index: 348117 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.9437. Min Act: -0.0000

Data Index: 206474 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1113830 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.9215. Min Act: -0.0000

Data Index: 147847 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1099286 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1347284 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.8433. Min Act: -0.0000

Data Index: 964807 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1195074 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1231367 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.7560. Min Act: -0.0000

Data Index: 201440 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.8689. Min Act: -0.0000

Data Index: 900980 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.7901. Min Act: -0.0000

Data Index: 151570 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.2782. Min Range: -1.2782

Max Act: 0.7562. Min Act: -0.0000

Data Index: 349834 (C4 (Web Text))

Max Activating Token Index: 194