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

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

Neuron 1860 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: 1.1977. Min Range: -1.1977

Max Act: 1.1977. Min Act: -0.0001

Data Index: 701494 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.9090. Min Act: -0.0001

Data Index: 446413 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.9062. Min Act: -0.0002

Data Index: 633325 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8345. Min Act: -0.0001

Data Index: 509721 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8709. Min Act: -0.0001

Data Index: 1074496 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8407. Min Act: -0.0001

Data Index: 346438 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8364. Min Act: -0.0001

Data Index: 527791 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8626. Min Act: -0.0001

Data Index: 374144 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8563. Min Act: -0.0001

Data Index: 1320236 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8277. Min Act: -0.0002

Data Index: 427225 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8978. Min Act: -0.0001

Data Index: 204032 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.7975. Min Act: -0.0002

Data Index: 143332 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.7957. Min Act: -0.0001

Data Index: 411282 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.7934. Min Act: -0.0001

Data Index: 350536 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.7436. Min Act: -0.0001

Data Index: 267582 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.8512. Min Act: -0.0001

Data Index: 1078309 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.7367. Min Act: -0.0001

Data Index: 221558 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.7496. Min Act: -0.0001

Data Index: 681801 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.7773. Min Act: -0.0001

Data Index: 982580 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.1977. Min Range: -1.1977

Max Act: 0.7845. Min Act: -0.0001

Data Index: 27438 (C4 (Web Text))

Max Activating Token Index: 265