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

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

Neuron 1017 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1542974 (Python Code)

Max Activating Token Index: 615

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1632917 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1457556 (Python Code)

Max Activating Token Index: 274

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0545. Min Act: -0.0002

Data Index: 67473 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1423527 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0585. Min Act: -0.0002

Data Index: 727804 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1168117 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1554439 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0556. Min Act: -0.0002

Data Index: 244634 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0502. Min Act: -0.0002

Data Index: 69919 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0455. Min Act: -0.0002

Data Index: 629187 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1482054 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0523. Min Act: -0.0002

Data Index: 194216 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0523. Min Act: -0.0002

Data Index: 151702 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0405. Min Act: -0.0002

Data Index: 434962 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0420. Min Act: -0.0002

Data Index: 608358 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0514. Min Act: -0.0002

Data Index: 829229 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0574. Min Act: -0.0002

Data Index: 435252 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0451. Min Act: -0.0002

Data Index: 931130 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0414. Min Act: -0.0002

Data Index: 168335 (C4 (Web Text))

Max Activating Token Index: 143