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

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

Neuron 5840 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1164463 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5866. Min Act: -0.0000

Data Index: 385512 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5398. Min Act: -0.0000

Data Index: 174061 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.5460. Min Act: -0.0000

Data Index: 250799 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1190280 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4878. Min Act: -0.0000

Data Index: 880822 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1000152 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1191513 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1329198 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4718. Min Act: -0.0000

Data Index: 683215 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4717. Min Act: -0.0000

Data Index: 978529 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4544. Min Act: -0.0000

Data Index: 19707 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4655. Min Act: -0.0000

Data Index: 58596 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4975. Min Act: -0.0000

Data Index: 602857 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1320206 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4371. Min Act: -0.0000

Data Index: 380386 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1054715 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4545. Min Act: -0.0000

Data Index: 488607 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1144405 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.6821. Min Range: -0.6821

Max Act: 0.4600. Min Act: -0.0000

Data Index: 807687 (C4 (Web Text))

Max Activating Token Index: 633