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

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

Neuron 3497 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0035. Min Range: -2.0035

Max Act: 2.0035. Min Act: -0.0000

Data Index: 1104287 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9876. Min Act: -0.0000

Data Index: 381878 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.7697. Min Act: -0.0000

Data Index: 1235245 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.7603. Min Act: -0.0000

Data Index: 571140 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8491. Min Act: -0.0000

Data Index: 1062440 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8511. Min Act: -0.0000

Data Index: 297115 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8136. Min Act: -0.0000

Data Index: 216641 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1240471 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8828. Min Act: -0.0000

Data Index: 226164 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.7732. Min Act: -0.0000

Data Index: 1219735 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.6840. Min Act: -0.0000

Data Index: 296458 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.5944. Min Act: -0.0000

Data Index: 275680 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1164135 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.6908. Min Act: -0.0000

Data Index: 897854 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.4869. Min Act: -0.0000

Data Index: 523010 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.6677. Min Act: -0.0000

Data Index: 590457 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.6070. Min Act: -0.0000

Data Index: 729352 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.6095. Min Act: -0.0000

Data Index: 541218 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.6086. Min Act: -0.0000

Data Index: 889840 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1314684 (C4 (Web Text))

Max Activating Token Index: 747