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

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

Neuron 3419 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1599. Min Act: -0.0001

Data Index: 828725 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1561856 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1381. Min Act: -0.0000

Data Index: 987157 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1296299 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1151. Min Act: -0.0000

Data Index: 69265 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1205298 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1240. Min Act: -0.0001

Data Index: 365534 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1377218 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1620675 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1484374 (Python Code)

Max Activating Token Index: 444

Text #10

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1416759 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1069. Min Act: -0.0000

Data Index: 815931 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1566431 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1400235 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1010087 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1079. Min Act: -0.0000

Data Index: 671327 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1032. Min Act: -0.0001

Data Index: 726723 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1546003 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1370486 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1054. Min Act: -0.0000

Data Index: 700643 (C4 (Web Text))

Max Activating Token Index: 589