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

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

Neuron 630 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: 0.7797. Min Range: -0.7797

Max Act: 0.7589. Min Act: -0.0000

Data Index: 912807 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1022656 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7797. Min Act: -0.0000

Data Index: 866675 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5930. Min Act: -0.0000

Data Index: 297363 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7083. Min Act: -0.0000

Data Index: 575949 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7385. Min Act: -0.0000

Data Index: 242268 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6219. Min Act: -0.0000

Data Index: 375114 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1325825 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1100517 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6670. Min Act: -0.0000

Data Index: 488127 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.7052. Min Act: -0.0000

Data Index: 119031 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6879. Min Act: -0.0000

Data Index: 364025 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6487. Min Act: -0.0000

Data Index: 439027 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6492. Min Act: -0.0000

Data Index: 535713 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5448. Min Act: -0.0000

Data Index: 255047 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5987. Min Act: -0.0000

Data Index: 206648 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5780. Min Act: -0.0000

Data Index: 488770 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1164302 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1289665 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.7797. Min Range: -0.7797

Max Act: 0.6374. Min Act: -0.0000

Data Index: 262042 (C4 (Web Text))

Max Activating Token Index: 683