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

Dataset: The Pile

Neuron 1909 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.4585. Min Act: -0.0000

Data Index: 1409421 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.4490. Min Act: -0.0000

Data Index: 1726449 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.4271. Min Act: -0.0000

Data Index: 200044 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.2073. Min Act: -0.0000

Data Index: 857105 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.3456. Min Act: -0.0000

Data Index: 942307 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.3046. Min Act: -0.0000

Data Index: 129621 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.7859. Min Act: -0.0000

Data Index: 333944 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1107184 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.1263. Min Act: -0.0000

Data Index: 1144047 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0864. Min Act: -0.0000

Data Index: 1380297 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.1538. Min Act: -0.0000

Data Index: 522424 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.2118. Min Act: -0.0000

Data Index: 962966 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1957383 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1188241 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1822402 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1799529 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0126. Min Act: -0.0000

Data Index: 444717 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0614. Min Act: -0.0000

Data Index: 159838 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0235. Min Act: -0.0000

Data Index: 977674 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0771. Min Act: -0.0000

Data Index: 774015 (The Pile)

Max Activating Token Index: 852