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

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

Neuron 1178 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: 0.9489. Min Range: -0.9489

Max Act: 0.9489. Min Act: -0.0000

Data Index: 29404 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.7515. Min Act: -0.0000

Data Index: 577954 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.7744. Min Act: -0.0000

Data Index: 775501 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.7389. Min Act: -0.0000

Data Index: 167903 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.7572. Min Act: -0.0001

Data Index: 207979 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6649. Min Act: -0.0000

Data Index: 208718 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6836. Min Act: -0.0001

Data Index: 490571 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6363. Min Act: -0.0001

Data Index: 427755 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1101313 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6497. Min Act: -0.0000

Data Index: 851211 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6187. Min Act: -0.0000

Data Index: 984470 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6542. Min Act: -0.0000

Data Index: 100124 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1100217 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6033. Min Act: -0.0001

Data Index: 1559463 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6207. Min Act: -0.0000

Data Index: 597585 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6148. Min Act: -0.0001

Data Index: 87250 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.5925. Min Act: -0.0000

Data Index: 332473 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6127. Min Act: -0.0001

Data Index: 120213 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1174158 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1213189 (C4 (Web Text))

Max Activating Token Index: 937