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

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

Neuron 1184 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.3199. Min Act: -0.0001

Data Index: 1060477 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.8063. Min Act: -0.0000

Data Index: 807373 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.4760. Min Act: -0.0001

Data Index: 315788 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.4530. Min Act: -0.0000

Data Index: 649951 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.2687. Min Act: -0.0001

Data Index: 906629 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.2302. Min Act: -0.0000

Data Index: 695345 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.1230. Min Act: -0.0000

Data Index: 851291 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.1743. Min Act: -0.0001

Data Index: 1057639 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.0689. Min Act: -0.0000

Data Index: 79300 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.1555. Min Act: -0.0000

Data Index: 266556 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.1195. Min Act: -0.0000

Data Index: 1239184 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 2.8063. Min Range: -2.8063

Max Act: 1.8544. Min Act: -0.0000

Data Index: 1032048 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 2.8063. Min Range: -2.8063

Max Act: 1.8965. Min Act: -0.0000

Data Index: 241048 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.8063. Min Range: -2.8063

Max Act: 1.8470. Min Act: -0.0000

Data Index: 1186031 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.1279. Min Act: -0.0000

Data Index: 1097119 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 2.8063. Min Range: -2.8063

Max Act: 2.0266. Min Act: -0.0000

Data Index: 311631 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 2.8063. Min Range: -2.8063

Max Act: 1.9255. Min Act: -0.0000

Data Index: 503072 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 2.8063. Min Range: -2.8063

Max Act: 1.9476. Min Act: -0.0000

Data Index: 16995 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 2.8063. Min Range: -2.8063

Max Act: 1.7826. Min Act: -0.0000

Data Index: 874680 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 2.8063. Min Range: -2.8063

Max Act: 1.9668. Min Act: -0.0000

Data Index: 961140 (C4 (Web Text))

Max Activating Token Index: 869