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

Dataset: The Pile

Neuron 5025 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.7913. Min Act: -0.0000

Data Index: 1758731 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 3.7913. Min Range: -3.7913

Max Act: 3.3271. Min Act: -0.0000

Data Index: 465166 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.7933. Min Act: -0.0000

Data Index: 482010 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.6218. Min Act: -0.0000

Data Index: 1984166 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.5016. Min Act: -0.0000

Data Index: 662199 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.6457. Min Act: -0.0000

Data Index: 38195 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1264348 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.6353. Min Act: -0.0000

Data Index: 708480 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.4571. Min Act: -0.0000

Data Index: 1239661 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.4152. Min Act: -0.0000

Data Index: 185384 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.4097. Min Act: -0.0000

Data Index: 383248 (The Pile)

Max Activating Token Index: 313

Text #11

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1233838 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1688704 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.1976. Min Act: -0.0000

Data Index: 1845711 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.1632. Min Act: -0.0000

Data Index: 186938 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1937917 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1104797 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1703159 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.2059. Min Act: -0.0000

Data Index: 545676 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 3.7913. Min Range: -3.7913

Max Act: 1.1447. Min Act: -0.0000

Data Index: 904841 (The Pile)

Max Activating Token Index: 973