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

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

Neuron 4924 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: 0.3627. Min Range: -0.3627

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1468667 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3627. Min Act: -0.0000

Data Index: 681789 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3320. Min Act: -0.0000

Data Index: 565481 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3201. Min Act: -0.0000

Data Index: 457756 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1103065 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2944. Min Act: -0.0000

Data Index: 933158 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2720. Min Act: -0.0000

Data Index: 233471 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1127245 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2842. Min Act: -0.0000

Data Index: 974465 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1204462 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2864. Min Act: -0.0000

Data Index: 379365 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2980. Min Act: -0.0000

Data Index: 273070 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2463. Min Act: -0.0000

Data Index: 157582 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3049. Min Act: -0.0000

Data Index: 50905 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2757. Min Act: -0.0000

Data Index: 65790 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2568. Min Act: -0.0000

Data Index: 75765 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1478396 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1583099 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1016986 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1051300 (C4 (Web Text))

Max Activating Token Index: 315