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

Dataset: The Pile

Neuron 630 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.6246. Min Act: -0.0000

Data Index: 1244188 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.5929. Min Act: -0.0000

Data Index: 1924659 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.3922. Min Act: -0.0000

Data Index: 286327 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.5114. Min Act: -0.0000

Data Index: 261388 (The Pile)

Max Activating Token Index: 311

Text #4

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4863. Min Act: -0.0000

Data Index: 1427716 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4638. Min Act: -0.0000

Data Index: 83492 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1232268 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4135. Min Act: -0.0000

Data Index: 1196647 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1543152 (The Pile)

Max Activating Token Index: 950

Text #9

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4464. Min Act: -0.0000

Data Index: 670459 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4380. Min Act: -0.0000

Data Index: 532393 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4420. Min Act: -0.0000

Data Index: 1538751 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4806. Min Act: -0.0000

Data Index: 1811174 (The Pile)

Max Activating Token Index: 274

Text #13

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4365. Min Act: -0.0000

Data Index: 1112734 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4638. Min Act: -0.0000

Data Index: 341791 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4248. Min Act: -0.0000

Data Index: 1617412 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.3821. Min Act: -0.0000

Data Index: 897157 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4654. Min Act: -0.0000

Data Index: 1297993 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.4435. Min Act: -0.0000

Data Index: 925867 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 1.6246. Min Range: -1.6246

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1216722 (The Pile)

Max Activating Token Index: 661