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

Dataset: The Pile

Neuron 1980 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: 0.5919. Min Range: -0.5919

Max Act: 0.5855. Min Act: -0.0000

Data Index: 403953 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1884412 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1700618 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5919. Min Act: -0.0000

Data Index: 3293 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5751. Min Act: -0.0000

Data Index: 455940 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5321. Min Act: -0.0000

Data Index: 538799 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1033237 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1458206 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1367286 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1521761 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4835. Min Act: -0.0000

Data Index: 363654 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1546606 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1645709 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5323. Min Act: -0.0000

Data Index: 878745 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1661358 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4983. Min Act: -0.0000

Data Index: 790980 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.4850. Min Act: -0.0000

Data Index: 726308 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5048. Min Act: -0.0000

Data Index: 598980 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1953359 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 0.5919. Min Range: -0.5919

Max Act: 0.5023. Min Act: -0.0000

Data Index: 435267 (The Pile)

Max Activating Token Index: 802