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

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

Neuron 2806 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: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1374813 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1629034 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0496. Min Act: -0.0003

Data Index: 387150 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1504790 (Python Code)

Max Activating Token Index: 349

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0453. Min Act: -0.0003

Data Index: 326795 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0451. Min Act: -0.0003

Data Index: 916876 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0450. Min Act: -0.0003

Data Index: 931415 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0441. Min Act: -0.0003

Data Index: 809105 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1031107 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0437. Min Act: -0.0003

Data Index: 140055 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0437. Min Act: -0.0003

Data Index: 346618 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1087446 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1277259 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1265809 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1116375 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1559975 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0431. Min Act: -0.0003

Data Index: 959863 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0413. Min Act: -0.0003

Data Index: 522763 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1013459 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0422. Min Act: -0.0003

Data Index: 197402 (C4 (Web Text))

Max Activating Token Index: 120