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

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

Neuron 3632 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0440. Min Range: -1.0440

Max Act: 1.0440. Min Act: -0.0001

Data Index: 831258 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 1.0440. Min Range: -1.0440

Max Act: 1.0369. Min Act: -0.0001

Data Index: 435093 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9783. Min Act: -0.0001

Data Index: 643023 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1004072 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1180052 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8758. Min Act: -0.0001

Data Index: 718109 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9090. Min Act: -0.0001

Data Index: 671374 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8825. Min Act: -0.0001

Data Index: 1274668 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8716. Min Act: -0.0001

Data Index: 1253771 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9244. Min Act: -0.0001

Data Index: 614749 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8932. Min Act: -0.0000

Data Index: 614807 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8284. Min Act: -0.0001

Data Index: 1021335 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9357. Min Act: -0.0000

Data Index: 471684 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7930. Min Act: -0.0001

Data Index: 470050 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7741. Min Act: -0.0000

Data Index: 947669 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8207. Min Act: -0.0000

Data Index: 292461 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7535. Min Act: -0.0001

Data Index: 715110 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8404. Min Act: -0.0001

Data Index: 853820 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1268596 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7493. Min Act: -0.0001

Data Index: 766082 (C4 (Web Text))

Max Activating Token Index: 569