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

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

Neuron 1707 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.8945. Min Act: -0.0000

Data Index: 857028 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.8999. Min Act: -0.0000

Data Index: 811109 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 3.1783. Min Range: -3.1783

Max Act: 3.1783. Min Act: -0.0000

Data Index: 1258594 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.8291. Min Act: -0.0000

Data Index: 652850 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.9523. Min Act: 0.0000

Data Index: 1270770 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 3.1783. Min Range: -3.1783

Max Act: 3.0189. Min Act: -0.0000

Data Index: 530891 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.8397. Min Act: -0.0000

Data Index: 573360 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.7961. Min Act: -0.0000

Data Index: 404940 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.9443. Min Act: -0.0000

Data Index: 540898 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.5042. Min Act: -0.0000

Data Index: 580992 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.5752. Min Act: -0.0000

Data Index: 754273 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.7228. Min Act: -0.0000

Data Index: 990197 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 3.1783. Min Range: -3.1783

Max Act: 3.1027. Min Act: -0.0000

Data Index: 494377 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.6463. Min Act: -0.0000

Data Index: 699473 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.5505. Min Act: -0.0000

Data Index: 257683 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.3534. Min Act: -0.0000

Data Index: 118845 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.3340. Min Act: -0.0000

Data Index: 229755 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.4382. Min Act: -0.0000

Data Index: 609921 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.3168. Min Act: -0.0000

Data Index: 444981 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.1783. Min Range: -3.1783

Max Act: 2.5855. Min Act: -0.0000

Data Index: 204964 (C4 (Web Text))

Max Activating Token Index: 688