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

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

Neuron 1913 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6538. Min Act: -0.0000

Data Index: 916741 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6734. Min Act: -0.0000

Data Index: 935952 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6805. Min Act: -0.0000

Data Index: 56466 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1162469 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6929. Min Act: -0.0000

Data Index: 194745 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1099451 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1295208 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1124110 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5986. Min Act: -0.0000

Data Index: 754121 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5962. Min Act: -0.0000

Data Index: 645370 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1157963 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.6210. Min Act: -0.0000

Data Index: 202326 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5618. Min Act: -0.0000

Data Index: 225460 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5580. Min Act: -0.0000

Data Index: 879661 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5523. Min Act: -0.0000

Data Index: 459463 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5178. Min Act: -0.0000

Data Index: 883688 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5519. Min Act: -0.0000

Data Index: 114063 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1245454 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5165. Min Act: -0.0000

Data Index: 221542 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.6929. Min Range: -0.6929

Max Act: 0.5071. Min Act: -0.0000

Data Index: 697571 (C4 (Web Text))

Max Activating Token Index: 371