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

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

Neuron 110 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: 0.8354. Min Range: -0.8354

Max Act: 0.8354. Min Act: -0.0002

Data Index: 857224 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.7150. Min Act: -0.0002

Data Index: 1321670 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6898. Min Act: -0.0001

Data Index: 1339218 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6838. Min Act: -0.0002

Data Index: 590491 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6623. Min Act: -0.0001

Data Index: 974573 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6487. Min Act: -0.0002

Data Index: 477076 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6304. Min Act: -0.0002

Data Index: 554806 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6254. Min Act: -0.0002

Data Index: 714619 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6011. Min Act: -0.0002

Data Index: 841479 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6307. Min Act: -0.0002

Data Index: 16127 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6103. Min Act: -0.0001

Data Index: 104868 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.5697. Min Act: -0.0001

Data Index: 37893 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.5898. Min Act: -0.0002

Data Index: 1175053 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.5837. Min Act: -0.0002

Data Index: 1207977 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.6009. Min Act: -0.0001

Data Index: 383245 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.5898. Min Act: -0.0001

Data Index: 997943 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.4676. Min Act: -0.0002

Data Index: 337711 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.5523. Min Act: -0.0002

Data Index: 361603 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.5434. Min Act: -0.0001

Data Index: 1305711 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.8354. Min Range: -0.8354

Max Act: 0.5950. Min Act: -0.0001

Data Index: 231647 (C4 (Web Text))

Max Activating Token Index: 777