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

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

Neuron 1327 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.3000. Min Act: -0.0000

Data Index: 856179 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.3382. Min Act: -0.0000

Data Index: 1274672 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.3211. Min Act: -0.0000

Data Index: 760795 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.2627. Min Act: -0.0000

Data Index: 1106679 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.1130. Min Act: -0.0000

Data Index: 1309537 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.2405. Min Act: -0.0000

Data Index: 1259913 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.1710. Min Act: -0.0000

Data Index: 324925 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.1580. Min Act: -0.0000

Data Index: 169739 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.1341. Min Act: -0.0000

Data Index: 555662 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1277141 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.9607. Min Act: -0.0000

Data Index: 170207 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.8702. Min Act: -0.0000

Data Index: 429636 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.1858. Min Act: -0.0000

Data Index: 936624 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.7397. Min Act: -0.0000

Data Index: 44623 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0425. Min Act: -0.0000

Data Index: 756192 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0624. Min Act: -0.0000

Data Index: 354494 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.8254. Min Act: -0.0000

Data Index: 202823 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0344. Min Act: -0.0000

Data Index: 800437 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1173500 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0289. Min Act: -0.0000

Data Index: 261765 (C4 (Web Text))

Max Activating Token Index: 942