Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3153 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0104. Min Act: -0.0001

Data Index: 983054 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9729. Min Act: -0.0001

Data Index: 241163 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0239. Min Act: -0.0001

Data Index: 460623 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9476. Min Act: -0.0001

Data Index: 122675 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9364. Min Act: -0.0001

Data Index: 50391 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9405. Min Act: -0.0001

Data Index: 1113914 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8862. Min Act: -0.0001

Data Index: 761281 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9363. Min Act: -0.0001

Data Index: 1037608 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8430. Min Act: -0.0001

Data Index: 633775 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8612. Min Act: -0.0001

Data Index: 1236441 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8770. Min Act: -0.0001

Data Index: 494892 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8702. Min Act: -0.0001

Data Index: 1091185 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8219. Min Act: -0.0001

Data Index: 650611 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8381. Min Act: -0.0001

Data Index: 1309866 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8641. Min Act: -0.0001

Data Index: 926379 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8116. Min Act: -0.0001

Data Index: 1217488 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8923. Min Act: -0.0001

Data Index: 684577 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7995. Min Act: -0.0001

Data Index: 934684 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7998. Min Act: -0.0001

Data Index: 1009444 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8398. Min Act: -0.0001

Data Index: 160110 (C4 (Web Text))

Max Activating Token Index: 124