Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 372 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.0762. Min Act: -0.0001

Data Index: 774034 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.1435. Min Act: -0.0001

Data Index: 114962 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.1085. Min Act: -0.0001

Data Index: 390848 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.0297. Min Act: -0.0001

Data Index: 59355 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.1195. Min Act: -0.0001

Data Index: 208721 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.0043. Min Act: -0.0001

Data Index: 364032 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.1007. Min Act: -0.0001

Data Index: 246912 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9911. Min Act: -0.0001

Data Index: 211034 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.0506. Min Act: -0.0001

Data Index: 873375 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.0065. Min Act: -0.0001

Data Index: 138863 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9613. Min Act: -0.0001

Data Index: 987702 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.0263. Min Act: -0.0001

Data Index: 617963 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9964. Min Act: -0.0001

Data Index: 66091 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9780. Min Act: -0.0001

Data Index: 943224 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9954. Min Act: -0.0001

Data Index: 1213058 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9828. Min Act: -0.0001

Data Index: 293222 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9769. Min Act: -0.0001

Data Index: 1359229 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9205. Min Act: -0.0001

Data Index: 898291 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9385. Min Act: -0.0001

Data Index: 873593 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8978. Min Act: -0.0001

Data Index: 884131 (C4 (Web Text))

Max Activating Token Index: 784