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

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

Neuron 5914 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.5228. Min Act: -0.0001

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.6548. Min Act: -0.0001

Data Index: 899267 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.6531. Min Act: -0.0001

Data Index: 1175844 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.6384. Min Act: -0.0001

Data Index: 589438 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.6098. Min Act: -0.0001

Data Index: 988208 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.1489. Min Act: -0.0001

Data Index: 699458 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.7275. Min Act: -0.0001

Data Index: 820183 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.5179. Min Act: -0.0001

Data Index: 328409 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.6131. Min Act: -0.0001

Data Index: 1181974 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.5286. Min Act: -0.0001

Data Index: 1055480 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.4816. Min Act: -0.0001

Data Index: 802490 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.3228. Min Act: -0.0001

Data Index: 50671 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.3466. Min Act: -0.0001

Data Index: 1192193 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.2322. Min Act: -0.0001

Data Index: 727399 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.4768. Min Act: -0.0001

Data Index: 579052 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.4775. Min Act: -0.0001

Data Index: 566670 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.6341. Min Act: -0.0001

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.6149. Min Act: -0.0001

Data Index: 392286 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.6172. Min Act: -0.0001

Data Index: 771929 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 3.7275. Min Range: -3.7275

Max Act: 3.4627. Min Act: -0.0001

Data Index: 423700 (C4 (Web Text))

Max Activating Token Index: 983