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

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

Neuron 1582 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.3929. Min Act: -0.0001

Data Index: 142472 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.5534. Min Act: -0.0001

Data Index: 56831 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.6263. Min Act: -0.0000

Data Index: 761534 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.4760. Min Act: -0.0001

Data Index: 100530 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.4928. Min Act: -0.0001

Data Index: 30428 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.3776. Min Act: -0.0000

Data Index: 991643 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.3789. Min Act: -0.0001

Data Index: 828633 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.4516. Min Act: -0.0001

Data Index: 866300 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.4723. Min Act: -0.0001

Data Index: 616556 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.3453. Min Act: -0.0001

Data Index: 237261 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2932. Min Act: -0.0000

Data Index: 572199 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.3019. Min Act: -0.0001

Data Index: 709253 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2524. Min Act: -0.0001

Data Index: 1129517 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2071. Min Act: -0.0001

Data Index: 1162114 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2448. Min Act: -0.0001

Data Index: 651990 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2320. Min Act: -0.0001

Data Index: 78200 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2520. Min Act: -0.0001

Data Index: 1353875 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.1804. Min Act: -0.0001

Data Index: 836343 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.1652. Min Act: -0.0001

Data Index: 416712 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2686. Min Act: -0.0000

Data Index: 797491 (C4 (Web Text))

Max Activating Token Index: 83