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

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

Neuron 3594 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.6516. Min Act: -0.0001

Data Index: 836239 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.4415. Min Act: -0.0001

Data Index: 156791 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.3806. Min Act: -0.0001

Data Index: 842121 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.3531. Min Act: -0.0001

Data Index: 1001945 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.4099. Min Act: -0.0001

Data Index: 811476 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.1792. Min Act: -0.0001

Data Index: 743006 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.2310. Min Act: -0.0001

Data Index: 1014560 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.2328. Min Act: -0.0001

Data Index: 1244414 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.1908. Min Act: -0.0001

Data Index: 216341 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.1956. Min Act: -0.0001

Data Index: 553781 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.1397. Min Act: -0.0001

Data Index: 631430 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.1760. Min Act: -0.0000

Data Index: 950348 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.1337. Min Act: -0.0001

Data Index: 458115 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.0245. Min Act: -0.0001

Data Index: 248166 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.1400. Min Act: -0.0001

Data Index: 88910 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.6516. Min Range: -1.6516

Max Act: 0.8839. Min Act: -0.0001

Data Index: 274143 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.0276. Min Act: -0.0001

Data Index: 871815 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.0198. Min Act: -0.0001

Data Index: 113023 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.0147. Min Act: -0.0001

Data Index: 717840 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 1.6516. Min Range: -1.6516

Max Act: 1.0801. Min Act: -0.0001

Data Index: 1163315 (C4 (Web Text))

Max Activating Token Index: 264