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

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

Neuron 124 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2935. Min Range: -2.2935

Max Act: 2.2935. Min Act: -0.0000

Data Index: 582204 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 2.2935. Min Range: -2.2935

Max Act: 2.0959. Min Act: -0.0000

Data Index: 469224 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.9641. Min Act: -0.0000

Data Index: 914879 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 2.2935. Min Range: -2.2935

Max Act: 2.0019. Min Act: -0.0000

Data Index: 754504 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.9121. Min Act: -0.0000

Data Index: 183284 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.9802. Min Act: -0.0000

Data Index: 529750 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.8368. Min Act: -0.0000

Data Index: 1141287 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.9230. Min Act: -0.0000

Data Index: 984771 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.6555. Min Act: -0.0000

Data Index: 830520 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.7375. Min Act: -0.0000

Data Index: 1157929 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.6400. Min Act: -0.0000

Data Index: 336376 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.7224. Min Act: -0.0000

Data Index: 945707 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.6918. Min Act: -0.0000

Data Index: 537473 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.7916. Min Act: -0.0000

Data Index: 1220921 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1140008 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.5647. Min Act: -0.0000

Data Index: 228293 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.6460. Min Act: -0.0000

Data Index: 469741 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.6414. Min Act: -0.0000

Data Index: 46347 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.6386. Min Act: -0.0000

Data Index: 450223 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 2.2935. Min Range: -2.2935

Max Act: 1.7137. Min Act: -0.0000

Data Index: 175406 (C4 (Web Text))

Max Activating Token Index: 780