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

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

Neuron 108 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4420. Min Range: -6.4420

Max Act: 6.4420. Min Act: -0.0000

Data Index: 167551 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.5919. Min Act: -0.0000

Data Index: 679996 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.7095. Min Act: -0.0000

Data Index: 217698 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.4660. Min Act: -0.0000

Data Index: 333170 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.2943. Min Act: -0.0000

Data Index: 1111186 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.0878. Min Act: -0.0000

Data Index: 520400 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.4362. Min Act: -0.0000

Data Index: 1206515 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.2241. Min Act: -0.0000

Data Index: 675621 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.9712. Min Act: -0.0000

Data Index: 839472 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.4111. Min Act: -0.0000

Data Index: 380605 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.3088. Min Act: -0.0000

Data Index: 16132 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.8396. Min Act: -0.0000

Data Index: 220729 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.3518. Min Act: -0.0000

Data Index: 726164 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.0019. Min Act: -0.0000

Data Index: 579657 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.9033. Min Act: -0.0000

Data Index: 272689 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.8710. Min Act: -0.0000

Data Index: 149950 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 6.4420. Min Range: -6.4420

Max Act: 5.0304. Min Act: -0.0000

Data Index: 552883 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.8129. Min Act: -0.0000

Data Index: 158866 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.6099. Min Act: -0.0000

Data Index: 1261894 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 6.4420. Min Range: -6.4420

Max Act: 4.9464. Min Act: -0.0000

Data Index: 941886 (C4 (Web Text))

Max Activating Token Index: 951