Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2364 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0389. Min Range: -1.0389

Max Act: 1.0389. Min Act: -0.0000

Data Index: 535260 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9650. Min Act: -0.0000

Data Index: 42093 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9330. Min Act: -0.0000

Data Index: 274673 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9171. Min Act: -0.0001

Data Index: 34510 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8465. Min Act: -0.0000

Data Index: 489824 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8849. Min Act: -0.0000

Data Index: 858192 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1183464 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7766. Min Act: 0.0000

Data Index: 756247 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7591. Min Act: -0.0000

Data Index: 739637 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7538. Min Act: -0.0000

Data Index: 988438 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1063099 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7622. Min Act: -0.0000

Data Index: 102322 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7177. Min Act: -0.0000

Data Index: 101484 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6765. Min Act: -0.0001

Data Index: 1185716 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6702. Min Act: -0.0000

Data Index: 107740 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6708. Min Act: -0.0000

Data Index: 756017 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6944. Min Act: -0.0000

Data Index: 431447 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6834. Min Act: -0.0000

Data Index: 364157 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6991. Min Act: -0.0000

Data Index: 21022 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6688. Min Act: -0.0000

Data Index: 561445 (C4 (Web Text))

Max Activating Token Index: 805