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

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

Neuron 2899 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: 3.2015. Min Range: -3.2015

Max Act: 3.2015. Min Act: -0.0000

Data Index: 172840 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 3.2015. Min Range: -3.2015

Max Act: 3.0903. Min Act: -0.0000

Data Index: 1250676 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 3.2015. Min Range: -3.2015

Max Act: 2.9952. Min Act: -0.0000

Data Index: 1036539 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 3.2015. Min Range: -3.2015

Max Act: 2.8355. Min Act: -0.0000

Data Index: 1073352 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.5420. Min Act: -0.0000

Data Index: 191147 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.5831. Min Act: -0.0000

Data Index: 1234317 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.4367. Min Act: -0.0000

Data Index: 168969 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.4610. Min Act: -0.0000

Data Index: 1293816 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.3218. Min Act: -0.0000

Data Index: 590908 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.3295. Min Act: -0.0000

Data Index: 999705 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1154857 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1336723 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1351539 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.2952. Min Act: -0.0000

Data Index: 470422 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.1721. Min Act: -0.0000

Data Index: 158817 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1327898 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1303484 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1021442 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.1229. Min Act: -0.0000

Data Index: 783838 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 3.2015. Min Range: -3.2015

Max Act: 1.1415. Min Act: -0.0000

Data Index: 195210 (C4 (Web Text))

Max Activating Token Index: 699