Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5641 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7933. Min Range: -4.7933

Max Act: 4.7933. Min Act: -0.0000

Data Index: 466090 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 4.7933. Min Range: -4.7933

Max Act: 4.5580. Min Act: -0.0000

Data Index: 1006510 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 4.7933. Min Range: -4.7933

Max Act: 4.2140. Min Act: -0.0000

Data Index: 536121 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 4.7933. Min Range: -4.7933

Max Act: 4.0474. Min Act: -0.0000

Data Index: 103355 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 4.7933. Min Range: -4.7933

Max Act: 4.0777. Min Act: -0.0000

Data Index: 1060323 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.8614. Min Act: -0.0000

Data Index: 563884 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.5155. Min Act: -0.0000

Data Index: 574668 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.8531. Min Act: -0.0000

Data Index: 1298869 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.6849. Min Act: -0.0000

Data Index: 58021 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.7406. Min Act: -0.0000

Data Index: 514831 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.9690. Min Act: -0.0000

Data Index: 220421 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.5144. Min Act: -0.0000

Data Index: 1232099 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.3413. Min Act: -0.0000

Data Index: 900023 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.7415. Min Act: -0.0000

Data Index: 1241423 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.2753. Min Act: -0.0000

Data Index: 1261092 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.4128. Min Act: -0.0000

Data Index: 325703 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.5724. Min Act: -0.0000

Data Index: 52773 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 4.7933. Min Range: -4.7933

Max Act: 2.9521. Min Act: -0.0000

Data Index: 54919 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.4867. Min Act: -0.0000

Data Index: 976809 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 4.7933. Min Range: -4.7933

Max Act: 3.3422. Min Act: -0.0000

Data Index: 962716 (C4 (Web Text))

Max Activating Token Index: 217