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

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

Neuron 2899 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.6136. Min Act: -0.0001

Data Index: 59202 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.4509. Min Act: -0.0001

Data Index: 1252549 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.3677. Min Act: -0.0001

Data Index: 446643 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.3040. Min Act: -0.0001

Data Index: 1283583 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1882. Min Act: -0.0001

Data Index: 379160 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.2056. Min Act: -0.0001

Data Index: 1230790 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.2310. Min Act: -0.0001

Data Index: 807859 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1828. Min Act: -0.0001

Data Index: 1273366 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.2447. Min Act: -0.0001

Data Index: 1097308 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1643. Min Act: -0.0001

Data Index: 1249786 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1622. Min Act: -0.0001

Data Index: 899473 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1604. Min Act: -0.0001

Data Index: 726117 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1516. Min Act: -0.0001

Data Index: 1278095 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0810. Min Act: -0.0001

Data Index: 460242 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1605. Min Act: -0.0001

Data Index: 269368 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1177. Min Act: -0.0001

Data Index: 64337 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1121. Min Act: -0.0001

Data Index: 862366 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1101. Min Act: -0.0001

Data Index: 166737 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1333. Min Act: -0.0001

Data Index: 635669 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0280. Min Act: -0.0001

Data Index: 1337519 (C4 (Web Text))

Max Activating Token Index: 936