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

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

Neuron 990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.1531. Min Act: -0.0000

Data Index: 611602 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9529. Min Act: -0.0001

Data Index: 1119416 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1318187 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8620. Min Act: -0.0000

Data Index: 778598 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7706. Min Act: -0.0000

Data Index: 860159 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1025977 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7933. Min Act: -0.0001

Data Index: 309689 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7879. Min Act: -0.0001

Data Index: 587502 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1062188 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7578. Min Act: -0.0000

Data Index: 617334 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7286. Min Act: -0.0001

Data Index: 1348070 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7427. Min Act: -0.0001

Data Index: 119299 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7299. Min Act: -0.0001

Data Index: 1219560 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.6887. Min Act: -0.0000

Data Index: 720011 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7562. Min Act: -0.0001

Data Index: 431945 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1169572 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.6973. Min Act: -0.0000

Data Index: 572395 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1331132 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7129. Min Act: -0.0001

Data Index: 716878 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.6867. Min Act: -0.0001

Data Index: 158346 (C4 (Web Text))

Max Activating Token Index: 61