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

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

Neuron 4587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1258596 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1161299 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9263. Min Act: -0.0000

Data Index: 436600 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1005351 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8888. Min Act: -0.0000

Data Index: 599227 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9172. Min Act: -0.0000

Data Index: 420563 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8725. Min Act: -0.0000

Data Index: 117064 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8969. Min Act: -0.0000

Data Index: 340689 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.9192. Min Act: -0.0000

Data Index: 292252 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8811. Min Act: -0.0000

Data Index: 701677 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8787. Min Act: -0.0000

Data Index: 749651 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8640. Min Act: -0.0000

Data Index: 360708 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1069790 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8547. Min Act: -0.0000

Data Index: 758304 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8318. Min Act: -0.0000

Data Index: 229954 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8485. Min Act: -0.0000

Data Index: 967917 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1060380 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1231780 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8198. Min Act: -0.0000

Data Index: 752008 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7893. Min Act: -0.0000

Data Index: 197330 (C4 (Web Text))

Max Activating Token Index: 993