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

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

Neuron 893 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7230. Min Range: -3.7230

Max Act: 3.7230. Min Act: -0.0001

Data Index: 207700 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 3.7230. Min Range: -3.7230

Max Act: 3.4338. Min Act: -0.0001

Data Index: 208494 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 3.7230. Min Range: -3.7230

Max Act: 3.4506. Min Act: -0.0001

Data Index: 154019 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 3.7230. Min Range: -3.7230

Max Act: 3.0504. Min Act: -0.0001

Data Index: 298964 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.7230. Min Range: -3.7230

Max Act: 3.0881. Min Act: -0.0001

Data Index: 169338 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 3.7230. Min Range: -3.7230

Max Act: 3.0167. Min Act: -0.0001

Data Index: 793594 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 3.7230. Min Range: -3.7230

Max Act: 3.0051. Min Act: -0.0001

Data Index: 702166 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.9937. Min Act: -0.0001

Data Index: 667547 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 3.7230. Min Range: -3.7230

Max Act: 3.0826. Min Act: -0.0001

Data Index: 577363 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.7128. Min Act: -0.0001

Data Index: 1562822 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.5433. Min Act: -0.0001

Data Index: 811261 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.6576. Min Act: -0.0001

Data Index: 456408 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.6375. Min Act: -0.0001

Data Index: 603053 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.7655. Min Act: -0.0001

Data Index: 1314030 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.4462. Min Act: -0.0001

Data Index: 740337 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.4374. Min Act: -0.0001

Data Index: 223991 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.4516. Min Act: -0.0001

Data Index: 329695 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.6867. Min Act: -0.0001

Data Index: 906474 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.6705. Min Act: -0.0001

Data Index: 639008 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 3.7230. Min Range: -3.7230

Max Act: 2.6223. Min Act: -0.0001

Data Index: 176758 (C4 (Web Text))

Max Activating Token Index: 287