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

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

Neuron 4139 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0513. Min Act: -0.0001

Data Index: 1289930 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0618. Min Act: -0.0001

Data Index: 381493 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0648. Min Act: -0.0001

Data Index: 1104116 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0093. Min Act: -0.0001

Data Index: 1216420 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0375. Min Act: -0.0001

Data Index: 294097 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9568. Min Act: -0.0001

Data Index: 803952 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0291. Min Act: -0.0001

Data Index: 219609 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0053. Min Act: -0.0001

Data Index: 592528 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0321. Min Act: -0.0001

Data Index: 88063 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9680. Min Act: -0.0001

Data Index: 987626 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9073. Min Act: -0.0000

Data Index: 115229 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8649. Min Act: -0.0001

Data Index: 21558 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9056. Min Act: -0.0001

Data Index: 1057486 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8276. Min Act: -0.0001

Data Index: 1283122 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9361. Min Act: -0.0001

Data Index: 200030 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9186. Min Act: -0.0001

Data Index: 291766 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8386. Min Act: -0.0001

Data Index: 449058 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8849. Min Act: -0.0001

Data Index: 1356127 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9969. Min Act: -0.0000

Data Index: 369635 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8627. Min Act: -0.0001

Data Index: 1026 (C4 (Web Text))

Max Activating Token Index: 207