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

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

Neuron 230 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.6599. Min Act: -0.0001

Data Index: 994995 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.5164. Min Act: -0.0000

Data Index: 588876 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.5499. Min Act: -0.0000

Data Index: 576018 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.3853. Min Act: -0.0000

Data Index: 657478 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.7528. Min Act: -0.0000

Data Index: 1015458 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4550. Min Act: -0.0000

Data Index: 985124 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.3225. Min Act: -0.0000

Data Index: 747930 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.2592. Min Act: -0.0000

Data Index: 236210 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.2490. Min Act: -0.0000

Data Index: 328198 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4846. Min Act: -0.0000

Data Index: 1228307 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4317. Min Act: -0.0000

Data Index: 981416 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1328544 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.1848. Min Act: -0.0000

Data Index: 1126159 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.1833. Min Act: -0.0000

Data Index: 524402 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.1686. Min Act: -0.0000

Data Index: 835184 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.2764. Min Act: -0.0000

Data Index: 403893 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.1629. Min Act: -0.0000

Data Index: 840396 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.2629. Min Act: -0.0000

Data Index: 1338928 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.2410. Min Act: -0.0000

Data Index: 869964 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.2283. Min Act: -0.0000

Data Index: 794527 (C4 (Web Text))

Max Activating Token Index: 791