Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1535 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0004

Data Index: 320578 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0576. Min Act: -0.0004

Data Index: 970919 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1083110 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0559. Min Act: -0.0004

Data Index: 409892 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0560. Min Act: -0.0003

Data Index: 244963 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1154027 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0529. Min Act: -0.0003

Data Index: 60460 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0522. Min Act: -0.0003

Data Index: 142600 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0505. Min Act: -0.0003

Data Index: 248501 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0502. Min Act: -0.0003

Data Index: 254120 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0495. Min Act: -0.0004

Data Index: 360045 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0497. Min Act: -0.0003

Data Index: 387432 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0489. Min Act: -0.0003

Data Index: 713522 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1247996 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1093691 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0486. Min Act: -0.0003

Data Index: 400818 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1200725 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1066008 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0468. Min Act: -0.0004

Data Index: 175789 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0459. Min Act: -0.0003

Data Index: 612274 (C4 (Web Text))

Max Activating Token Index: 491