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

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

Neuron 4593 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: 2.4450. Min Range: -2.4450

Max Act: 2.4450. Min Act: -0.0000

Data Index: 451056 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.3950. Min Act: -0.0000

Data Index: 1194443 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.4085. Min Act: -0.0000

Data Index: 24861 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.3170. Min Act: -0.0000

Data Index: 471894 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.2980. Min Act: -0.0000

Data Index: 180423 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.1779. Min Act: -0.0000

Data Index: 568286 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.2576. Min Act: -0.0000

Data Index: 746970 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.2078. Min Act: -0.0000

Data Index: 969588 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.0564. Min Act: -0.0000

Data Index: 509807 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.1626. Min Act: -0.0000

Data Index: 1191516 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.1163. Min Act: -0.0000

Data Index: 1348120 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.1116. Min Act: -0.0000

Data Index: 435015 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.0731. Min Act: -0.0000

Data Index: 852972 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.0709. Min Act: -0.0000

Data Index: 942151 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.0645. Min Act: -0.0000

Data Index: 87884 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.0081. Min Act: -0.0000

Data Index: 510909 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.0011. Min Act: -0.0000

Data Index: 1151361 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 2.4450. Min Range: -2.4450

Max Act: 2.0057. Min Act: -0.0000

Data Index: 203040 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 2.4450. Min Range: -2.4450

Max Act: 1.9890. Min Act: -0.0000

Data Index: 79368 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 2.4450. Min Range: -2.4450

Max Act: 1.8839. Min Act: -0.0000

Data Index: 355520 (C4 (Web Text))

Max Activating Token Index: 132