Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4683 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.8270. Min Act: -0.0000

Data Index: 163004 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.7339. Min Act: -0.0000

Data Index: 734004 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.8157. Min Act: -0.0000

Data Index: 81737 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.6883. Min Act: -0.0000

Data Index: 714179 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1562310 (Python Code)

Max Activating Token Index: 948

Text #5

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.6785. Min Act: -0.0000

Data Index: 1422102 (Python Code)

Max Activating Token Index: 446

Text #6

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.7468. Min Act: -0.0000

Data Index: 851459 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.7036. Min Act: -0.0000

Data Index: 251417 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.6061. Min Act: -0.0000

Data Index: 415270 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.5676. Min Act: -0.0000

Data Index: 1530842 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.6405. Min Act: -0.0000

Data Index: 1398715 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.5049. Min Act: -0.0000

Data Index: 810543 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.4878. Min Act: -0.0000

Data Index: 1278978 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.4936. Min Act: -0.0000

Data Index: 268513 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.4499. Min Act: -0.0000

Data Index: 418575 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.4700. Min Act: -0.0000

Data Index: 760628 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1538725 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.4269. Min Act: -0.0000

Data Index: 1588192 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.5555. Min Act: -0.0000

Data Index: 621432 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.4540. Min Act: -0.0000

Data Index: 409008 (C4 (Web Text))

Max Activating Token Index: 378