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

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

Neuron 1546 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: 0.8494. Min Range: -0.8494

Max Act: 0.7876. Min Act: -0.0002

Data Index: 1356830 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7832. Min Act: -0.0002

Data Index: 217762 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7957. Min Act: -0.0002

Data Index: 1103346 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.8494. Min Act: -0.0001

Data Index: 1226209 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7472. Min Act: -0.0002

Data Index: 754272 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7883. Min Act: -0.0001

Data Index: 316621 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7264. Min Act: -0.0001

Data Index: 1203177 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6916. Min Act: -0.0002

Data Index: 72403 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7543. Min Act: -0.0001

Data Index: 609025 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6598. Min Act: -0.0002

Data Index: 693811 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6907. Min Act: -0.0001

Data Index: 1151071 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7078. Min Act: -0.0002

Data Index: 196960 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7052. Min Act: -0.0002

Data Index: 44392 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.7468. Min Act: -0.0002

Data Index: 674178 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6838. Min Act: -0.0001

Data Index: 1214132 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6483. Min Act: -0.0002

Data Index: 1272433 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6711. Min Act: -0.0002

Data Index: 207190 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6670. Min Act: -0.0001

Data Index: 606129 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6823. Min Act: -0.0002

Data Index: 425559 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.8494. Min Range: -0.8494

Max Act: 0.6818. Min Act: -0.0002

Data Index: 83340 (C4 (Web Text))

Max Activating Token Index: 973