Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2041 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1124374 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0622. Min Act: -0.0002

Data Index: 800486 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0571. Min Act: -0.0002

Data Index: 840675 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0552. Min Act: -0.0001

Data Index: 55445 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0537. Min Act: -0.0001

Data Index: 823801 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1260639 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0518. Min Act: -0.0002

Data Index: 515712 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0532. Min Act: -0.0002

Data Index: 939181 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0498. Min Act: 0.0000

Data Index: 1640196 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1293564 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0483. Min Act: -0.0002

Data Index: 472718 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0481. Min Act: -0.0002

Data Index: 506861 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0496. Min Act: -0.0002

Data Index: 443578 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0477. Min Act: -0.0002

Data Index: 4160 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1029254 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0489. Min Act: -0.0002

Data Index: 536242 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0464. Min Act: -0.0002

Data Index: 953811 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0465. Min Act: -0.0001

Data Index: 713991 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0473. Min Act: -0.0001

Data Index: 61654 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0477. Min Act: -0.0002

Data Index: 257806 (C4 (Web Text))

Max Activating Token Index: 911