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

Dataset: The Pile

Neuron 2012 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: 0.4821. Min Range: -0.4821

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1602021 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1069591 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3371. Min Act: -0.0000

Data Index: 888417 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1520585 (The Pile)

Max Activating Token Index: 549

Text #4

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1630579 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1700359 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1670809 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1505687 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3084. Min Act: -0.0000

Data Index: 310763 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3082. Min Act: -0.0000

Data Index: 904260 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3071. Min Act: -0.0000

Data Index: 330553 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1514666 (The Pile)

Max Activating Token Index: 328

Text #12

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1850835 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.2725. Min Act: -0.0000

Data Index: 355090 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.2750. Min Act: -0.0000

Data Index: 387936 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1156124 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.2918. Min Act: -0.0000

Data Index: 182253 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1021903 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1475554 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.4821. Min Range: -0.4821

Max Act: 0.2887. Min Act: -0.0000

Data Index: 904803 (The Pile)

Max Activating Token Index: 365