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

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

Neuron 971 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: 3.2947. Min Range: -3.2947

Max Act: 3.2947. Min Act: -0.0000

Data Index: 711261 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.8909. Min Act: -0.0000

Data Index: 1055969 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.6929. Min Act: -0.0000

Data Index: 1212219 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.9484. Min Act: -0.0000

Data Index: 688496 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.9485. Min Act: -0.0001

Data Index: 745738 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.6466. Min Act: -0.0000

Data Index: 1190679 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.9093. Min Act: -0.0000

Data Index: 45832 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.7365. Min Act: -0.0000

Data Index: 1147504 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.8364. Min Act: -0.0000

Data Index: 280406 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.6657. Min Act: -0.0000

Data Index: 264942 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.7752. Min Act: -0.0000

Data Index: 651501 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.6074. Min Act: -0.0000

Data Index: 742045 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.7341. Min Act: -0.0000

Data Index: 930605 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.4746. Min Act: -0.0000

Data Index: 946571 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.5859. Min Act: -0.0001

Data Index: 767799 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.4253. Min Act: -0.0000

Data Index: 827585 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.6774. Min Act: -0.0000

Data Index: 1164913 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.4256. Min Act: -0.0000

Data Index: 506836 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.5268. Min Act: -0.0000

Data Index: 1307521 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.2947. Min Range: -3.2947

Max Act: 2.5221. Min Act: -0.0000

Data Index: 707567 (C4 (Web Text))

Max Activating Token Index: 651