Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3766 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1442. Min Act: -0.0000

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1360. Min Act: -0.0000

Data Index: 544864 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1198. Min Act: -0.0000

Data Index: 796421 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1144. Min Act: -0.0000

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1074. Min Act: -0.0000

Data Index: 281554 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1066. Min Act: -0.0000

Data Index: 506800 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1101. Min Act: -0.0001

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1045. Min Act: -0.0000

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1045. Min Act: -0.0000

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1000. Min Act: -0.0000

Data Index: 33911 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1053. Min Act: -0.0000

Data Index: 78349 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1000. Min Act: -0.0001

Data Index: 357008 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1041875 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0991. Min Act: -0.0001

Data Index: 847637 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0912. Min Act: -0.0001

Data Index: 47265 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1327310 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0971. Min Act: -0.0000

Data Index: 98817 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0966. Min Act: -0.0000

Data Index: 509352 (C4 (Web Text))

Max Activating Token Index: 964