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

Dataset: The Pile

Neuron 357 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.1236. Min Act: -0.0000

Data Index: 413363 (The Pile)

Max Activating Token Index: 162

Text #1

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1746404 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.1071. Min Act: -0.0000

Data Index: 662289 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1094337 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1315057 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1302997 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0903. Min Act: -0.0000

Data Index: 903150 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1312531 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1415223 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1489603 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0980. Min Act: -0.0000

Data Index: 541921 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1304382 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1748005 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1513510 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1274132 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0803. Min Act: -0.0000

Data Index: 647122 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0852. Min Act: -0.0000

Data Index: 208912 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1099177 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1640660 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 0.1236. Min Range: -0.1236

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1629320 (The Pile)

Max Activating Token Index: 926