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

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

Neuron 80 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4992. Min Act: -0.0000

Data Index: 486196 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1631462 (Python Code)

Max Activating Token Index: 169

Text #2

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1210929 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4048. Min Act: -0.0000

Data Index: 904892 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4054. Min Act: -0.0000

Data Index: 7295 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4012. Min Act: -0.0000

Data Index: 175154 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3680. Min Act: -0.0000

Data Index: 106787 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.4048. Min Act: -0.0000

Data Index: 602649 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3519. Min Act: -0.0000

Data Index: 113500 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3704. Min Act: -0.0000

Data Index: 755948 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3368. Min Act: -0.0000

Data Index: 400439 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3436. Min Act: -0.0000

Data Index: 367699 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3200. Min Act: -0.0000

Data Index: 848429 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3691. Min Act: -0.0000

Data Index: 474966 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1240103 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3203. Min Act: -0.0000

Data Index: 904986 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1224330 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1240864 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.3088. Min Act: -0.0000

Data Index: 342003 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.4992. Min Range: -0.4992

Max Act: 0.2916. Min Act: -0.0000

Data Index: 235099 (C4 (Web Text))

Max Activating Token Index: 784