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

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

Neuron 3455 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3031. Min Range: -3.3031

Max Act: 3.3031. Min Act: -0.0001

Data Index: 194090 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.8328. Min Act: -0.0000

Data Index: 742166 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.9285. Min Act: -0.0000

Data Index: 389890 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.6937. Min Act: -0.0000

Data Index: 1249729 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.3637. Min Act: -0.0000

Data Index: 1204423 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.4175. Min Act: -0.0000

Data Index: 889402 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.5348. Min Act: -0.0000

Data Index: 433108 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.2817. Min Act: -0.0000

Data Index: 980120 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.2973. Min Act: -0.0000

Data Index: 420175 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.3972. Min Act: -0.0001

Data Index: 409500 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.2633. Min Act: -0.0001

Data Index: 1352401 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.5045. Min Act: -0.0001

Data Index: 541518 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.3455. Min Act: -0.0001

Data Index: 1161056 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.2376. Min Act: -0.0001

Data Index: 672339 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.2430. Min Act: -0.0000

Data Index: 697087 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.2297. Min Act: -0.0001

Data Index: 1013979 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.3131. Min Act: -0.0000

Data Index: 1106353 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.2901. Min Act: -0.0001

Data Index: 863902 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.3977. Min Act: -0.0000

Data Index: 1248153 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 3.3031. Min Range: -3.3031

Max Act: 2.1470. Min Act: -0.0000

Data Index: 1060070 (C4 (Web Text))

Max Activating Token Index: 967