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

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

Neuron 1057 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.4132. Min Act: -0.0001

Data Index: 1172447 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.4507. Min Act: -0.0001

Data Index: 481915 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2876. Min Act: -0.0001

Data Index: 442400 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2138. Min Act: -0.0001

Data Index: 788065 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2325. Min Act: -0.0001

Data Index: 1329333 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2463. Min Act: -0.0001

Data Index: 604955 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.1525. Min Act: -0.0001

Data Index: 675655 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2590. Min Act: -0.0001

Data Index: 949253 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.3345. Min Act: -0.0001

Data Index: 436594 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.1112. Min Act: -0.0001

Data Index: 544864 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2768. Min Act: -0.0001

Data Index: 158571 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.1948. Min Act: -0.0001

Data Index: 701243 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.0479. Min Act: -0.0001

Data Index: 875617 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.1233. Min Act: -0.0001

Data Index: 1171951 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.3304. Min Act: -0.0001

Data Index: 1143151 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2573. Min Act: -0.0001

Data Index: 202629 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2130. Min Act: -0.0001

Data Index: 973893 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2425. Min Act: -0.0001

Data Index: 1354814 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.2380. Min Act: -0.0001

Data Index: 776938 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.4507. Min Range: -1.4507

Max Act: 1.0932. Min Act: -0.0001

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 279