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

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

Neuron 1653 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: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0002

Data Index: 481556 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0582. Min Act: -0.0002

Data Index: 787569 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0512. Min Act: -0.0002

Data Index: 987566 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0520. Min Act: -0.0003

Data Index: 983961 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0487. Min Act: -0.0003

Data Index: 400428 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0463. Min Act: -0.0002

Data Index: 959968 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1131921 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1234900 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0455. Min Act: -0.0002

Data Index: 103389 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1085596 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0462. Min Act: -0.0002

Data Index: 751680 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1306425 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0440. Min Act: -0.0003

Data Index: 621454 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0448. Min Act: -0.0002

Data Index: 800049 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1145042 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1242588 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1334445 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0424. Min Act: -0.0003

Data Index: 628808 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0412. Min Act: -0.0003

Data Index: 390402 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0421. Min Act: -0.0002

Data Index: 156379 (C4 (Web Text))

Max Activating Token Index: 511