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

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

Neuron 3526 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.4078. Min Act: -0.0001

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3878. Min Act: -0.0001

Data Index: 1343291 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3143. Min Act: -0.0001

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3132. Min Act: -0.0001

Data Index: 525298 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3192. Min Act: -0.0001

Data Index: 588563 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3280. Min Act: -0.0001

Data Index: 344200 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3036. Min Act: -0.0001

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2635. Min Act: -0.0001

Data Index: 1655023 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2780. Min Act: -0.0001

Data Index: 759035 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2932. Min Act: -0.0001

Data Index: 1178075 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3118. Min Act: -0.0001

Data Index: 1378461 (Python Code)

Max Activating Token Index: 897

Text #11

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2657. Min Act: -0.0001

Data Index: 1606481 (Python Code)

Max Activating Token Index: 272

Text #12

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3049. Min Act: -0.0001

Data Index: 815488 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1446502 (Python Code)

Max Activating Token Index: 768

Text #14

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2824. Min Act: -0.0001

Data Index: 864063 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2817. Min Act: -0.0001

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2631. Min Act: -0.0001

Data Index: 1509173 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1322916 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1496959 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2850. Min Act: -0.0001

Data Index: 100449 (C4 (Web Text))

Max Activating Token Index: 567