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

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

Neuron 5998 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7870. Min Range: -6.7870

Max Act: 6.7870. Min Act: -0.0000

Data Index: 1212264 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 6.7870. Min Range: -6.7870

Max Act: 6.7207. Min Act: -0.0000

Data Index: 961890 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 6.7870. Min Range: -6.7870

Max Act: 6.1432. Min Act: -0.0000

Data Index: 719440 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.7163. Min Act: -0.0000

Data Index: 979662 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.8640. Min Act: -0.0000

Data Index: 836558 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.5388. Min Act: -0.0000

Data Index: 50867 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.1791. Min Act: -0.0000

Data Index: 348585 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 6.7870. Min Range: -6.7870

Max Act: 4.9159. Min Act: -0.0000

Data Index: 1098901 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.2982. Min Act: -0.0000

Data Index: 923169 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.4621. Min Act: -0.0000

Data Index: 611793 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.1975. Min Act: -0.0000

Data Index: 106347 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.0917. Min Act: -0.0000

Data Index: 1327727 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 6.7870. Min Range: -6.7870

Max Act: 5.0038. Min Act: -0.0000

Data Index: 678658 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 6.7870. Min Range: -6.7870

Max Act: 4.9185. Min Act: -0.0000

Data Index: 146677 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 6.7870. Min Range: -6.7870

Max Act: 4.9155. Min Act: -0.0000

Data Index: 403374 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 6.7870. Min Range: -6.7870

Max Act: 4.8532. Min Act: -0.0000

Data Index: 736471 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 6.7870. Min Range: -6.7870

Max Act: 4.6291. Min Act: -0.0000

Data Index: 1340114 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 6.7870. Min Range: -6.7870

Max Act: 4.6216. Min Act: -0.0000

Data Index: 900306 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 6.7870. Min Range: -6.7870

Max Act: 4.6168. Min Act: -0.0000

Data Index: 97148 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 6.7870. Min Range: -6.7870

Max Act: 4.9238. Min Act: -0.0000

Data Index: 644864 (C4 (Web Text))

Max Activating Token Index: 148