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

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

Neuron 1540 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.0524. Min Act: -0.0000

Data Index: 516411 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.2832. Min Act: -0.0000

Data Index: 333677 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.5547. Min Act: -0.0000

Data Index: 1349462 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.9313. Min Act: -0.0000

Data Index: 1014474 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.8905. Min Act: -0.0000

Data Index: 78170 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.9994. Min Act: -0.0000

Data Index: 975252 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.5561. Min Act: -0.0000

Data Index: 970942 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.5420. Min Act: -0.0000

Data Index: 558905 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.6113. Min Act: -0.0000

Data Index: 1234810 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.5459. Min Act: -0.0000

Data Index: 824145 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.6042. Min Act: -0.0000

Data Index: 1136761 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.3155. Min Act: -0.0000

Data Index: 903932 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.4069. Min Act: -0.0000

Data Index: 1181744 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.3424. Min Act: -0.0000

Data Index: 1301046 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.2097. Min Act: -0.0000

Data Index: 538444 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.1737. Min Act: -0.0000

Data Index: 305424 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.1533. Min Act: -0.0000

Data Index: 301875 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.0776. Min Act: -0.0000

Data Index: 491812 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.1797. Min Act: -0.0000

Data Index: 428462 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 3.2832. Min Range: -3.2832

Max Act: 2.1421. Min Act: -0.0000

Data Index: 1056261 (C4 (Web Text))

Max Activating Token Index: 566