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

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

Neuron 3025 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5832. Min Act: -0.0002

Data Index: 691572 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.6395. Min Act: -0.0001

Data Index: 60623 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.6044. Min Act: -0.0001

Data Index: 952571 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5613. Min Act: -0.0001

Data Index: 11261 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5387. Min Act: -0.0001

Data Index: 808861 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5347. Min Act: -0.0001

Data Index: 541820 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5089. Min Act: -0.0002

Data Index: 1221961 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5601. Min Act: -0.0002

Data Index: 545290 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4761. Min Act: -0.0001

Data Index: 89145 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4881. Min Act: -0.0001

Data Index: 799482 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5048. Min Act: -0.0001

Data Index: 410145 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4804. Min Act: -0.0002

Data Index: 599188 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1053212 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4911. Min Act: -0.0002

Data Index: 115142 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4698. Min Act: -0.0001

Data Index: 731175 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4670. Min Act: -0.0001

Data Index: 510843 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4365. Min Act: -0.0001

Data Index: 702609 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4790. Min Act: -0.0001

Data Index: 1103430 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5035. Min Act: -0.0001

Data Index: 740389 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.4409. Min Act: -0.0001

Data Index: 669860 (C4 (Web Text))

Max Activating Token Index: 345