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

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

Neuron 2662 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.3531. Min Act: -0.0000

Data Index: 1529760 (Python Code)

Max Activating Token Index: 970

Text #1

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.3082. Min Act: -0.0001

Data Index: 1508258 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1132. Min Act: -0.0001

Data Index: 679738 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.2138. Min Act: -0.0001

Data Index: 1477525 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1235. Min Act: -0.0001

Data Index: 1136201 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1079. Min Act: -0.0000

Data Index: 1485782 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0237. Min Act: -0.0001

Data Index: 466086 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1307. Min Act: -0.0001

Data Index: 709150 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1250. Min Act: -0.0001

Data Index: 1567329 (Python Code)

Max Activating Token Index: 559

Text #9

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0458. Min Act: -0.0001

Data Index: 290311 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0335. Min Act: -0.0001

Data Index: 2506 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0383. Min Act: -0.0001

Data Index: 1419415 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0474. Min Act: -0.0001

Data Index: 171866 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.9705. Min Act: -0.0001

Data Index: 337505 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.9937. Min Act: -0.0001

Data Index: 656272 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.1254. Min Act: -0.0001

Data Index: 1179304 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.9870. Min Act: -0.0001

Data Index: 1496943 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0250. Min Act: -0.0001

Data Index: 709567 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.3531. Min Range: -1.3531

Max Act: 0.9657. Min Act: -0.0001

Data Index: 71528 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.3531. Min Range: -1.3531

Max Act: 1.0007. Min Act: -0.0001

Data Index: 1576619 (Python Code)

Max Activating Token Index: 58