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

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

Neuron 4215 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: 1.5772. Min Range: -1.5772

Max Act: 1.5416. Min Act: -0.0000

Data Index: 1298186 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.5772. Min Act: -0.0000

Data Index: 1110255 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1144801 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1090774 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2361. Min Act: -0.0000

Data Index: 807028 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2753. Min Act: -0.0000

Data Index: 240494 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.3389. Min Act: -0.0000

Data Index: 735462 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.3462. Min Act: -0.0000

Data Index: 942344 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2648. Min Act: -0.0000

Data Index: 213975 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2694. Min Act: -0.0000

Data Index: 245280 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2712. Min Act: -0.0000

Data Index: 1183019 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2122. Min Act: -0.0000

Data Index: 232040 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.1544. Min Act: -0.0000

Data Index: 124596 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2146. Min Act: -0.0000

Data Index: 1152395 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1114981 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.1792. Min Act: -0.0000

Data Index: 565425 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.1848. Min Act: -0.0000

Data Index: 863740 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1240977 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.1429. Min Act: -0.0000

Data Index: 940352 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.5772. Min Range: -1.5772

Max Act: 1.2371. Min Act: -0.0000

Data Index: 710519 (C4 (Web Text))

Max Activating Token Index: 64