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

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

Neuron 23 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: 0.0699. Min Range: -0.0699

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1324450 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0578. Min Act: -0.0002

Data Index: 173148 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0559. Min Act: -0.0003

Data Index: 786623 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0543. Min Act: -0.0002

Data Index: 719409 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0504. Min Act: -0.0003

Data Index: 847790 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0480. Min Act: -0.0003

Data Index: 608996 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0507. Min Act: -0.0002

Data Index: 619422 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0479. Min Act: -0.0002

Data Index: 262917 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0497. Min Act: -0.0002

Data Index: 852496 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0480. Min Act: -0.0003

Data Index: 580633 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1296470 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1243105 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0455. Min Act: -0.0002

Data Index: 266482 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0442. Min Act: -0.0002

Data Index: 872322 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1078973 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1181409 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0447. Min Act: -0.0003

Data Index: 673736 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1263226 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1184279 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0418. Min Act: -0.0003

Data Index: 444440 (C4 (Web Text))

Max Activating Token Index: 155