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

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

Neuron 4164 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0446. Min Act: -0.0001

Data Index: 705392 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0476. Min Act: -0.0001

Data Index: 116712 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0505. Min Act: -0.0001

Data Index: 606532 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0494. Min Act: -0.0001

Data Index: 855973 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0001

Data Index: 146803 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0500. Min Act: -0.0001

Data Index: 958015 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1276793 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0532. Min Act: -0.0001

Data Index: 181803 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0494. Min Act: -0.0001

Data Index: 452161 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0457. Min Act: -0.0001

Data Index: 385417 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0440. Min Act: -0.0001

Data Index: 936444 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0435. Min Act: -0.0001

Data Index: 253393 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0498. Min Act: -0.0001

Data Index: 464414 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1162004 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0462. Min Act: -0.0001

Data Index: 654887 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0459. Min Act: -0.0001

Data Index: 127320 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0407. Min Act: -0.0001

Data Index: 533671 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1023439 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1304338 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1211110 (C4 (Web Text))

Max Activating Token Index: 737