Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3186 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1187884 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1978653 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7907. Min Act: -0.0000

Data Index: 461267 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7908. Min Act: -0.0000

Data Index: 985591 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1202118 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.8015. Min Act: -0.0000

Data Index: 868573 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1480164 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1577050 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7549. Min Act: -0.0000

Data Index: 414059 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7051. Min Act: -0.0000

Data Index: 48267 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1384697 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7657. Min Act: -0.0000

Data Index: 25355 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7348. Min Act: -0.0000

Data Index: 70592 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6981. Min Act: -0.0000

Data Index: 761083 (The Pile)

Max Activating Token Index: 228

Text #14

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1478928 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1430964 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6539. Min Act: -0.0000

Data Index: 725350 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7135. Min Act: -0.0000

Data Index: 134866 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6586. Min Act: -0.0000

Data Index: 889962 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1322786 (The Pile)

Max Activating Token Index: 338