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

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

Neuron 2628 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: 4.7829. Min Range: -4.7829

Max Act: 4.7292. Min Act: -0.0000

Data Index: 671972 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 4.7829. Min Range: -4.7829

Max Act: 4.7829. Min Act: -0.0000

Data Index: 730544 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 4.7829. Min Range: -4.7829

Max Act: 4.2810. Min Act: -0.0000

Data Index: 1232897 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.8705. Min Act: -0.0000

Data Index: 263544 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.8787. Min Act: -0.0000

Data Index: 766698 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.4309. Min Act: -0.0000

Data Index: 1188261 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.3861. Min Act: -0.0000

Data Index: 50684 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.3776. Min Act: -0.0000

Data Index: 4165 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.4910. Min Act: -0.0000

Data Index: 1089877 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.2936. Min Act: -0.0000

Data Index: 1101082 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.2892. Min Act: -0.0000

Data Index: 1057862 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.0693. Min Act: -0.0000

Data Index: 348273 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.1843. Min Act: -0.0000

Data Index: 290212 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.1663. Min Act: -0.0000

Data Index: 153774 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.1556. Min Act: -0.0000

Data Index: 376178 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.3068. Min Act: -0.0000

Data Index: 762212 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.2993. Min Act: -0.0000

Data Index: 48956 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.2996. Min Act: -0.0000

Data Index: 1135981 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.2522. Min Act: -0.0000

Data Index: 1153482 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 4.7829. Min Range: -4.7829

Max Act: 3.2435. Min Act: -0.0000

Data Index: 351239 (C4 (Web Text))

Max Activating Token Index: 814