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

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

Neuron 3447 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0003

Data Index: 1297178 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0687. Min Act: -0.0003

Data Index: 366927 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0669. Min Act: -0.0003

Data Index: 60340 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0605. Min Act: -0.0003

Data Index: 987246 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0593. Min Act: -0.0003

Data Index: 956196 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1296695 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0592. Min Act: -0.0003

Data Index: 918213 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0570. Min Act: -0.0003

Data Index: 801870 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0539. Min Act: -0.0003

Data Index: 509486 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1084035 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1067257 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0518. Min Act: -0.0003

Data Index: 121262 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0512. Min Act: -0.0003

Data Index: 543751 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1259736 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1126330 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1008178 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0490. Min Act: -0.0003

Data Index: 921394 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1329793 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0493. Min Act: -0.0003

Data Index: 960998 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1253496 (C4 (Web Text))

Max Activating Token Index: 136