Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2298 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.8162. Min Act: -0.0001

Data Index: 1441130 (Python Code)

Max Activating Token Index: 688

Text #1

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5677. Min Act: -0.0000

Data Index: 949247 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5389. Min Act: -0.0001

Data Index: 1470613 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1069315 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5171. Min Act: -0.0001

Data Index: 1397443 (Python Code)

Max Activating Token Index: 847

Text #5

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5144. Min Act: -0.0000

Data Index: 915313 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5285. Min Act: -0.0001

Data Index: 1524235 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4975. Min Act: -0.0001

Data Index: 1494900 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4615. Min Act: -0.0000

Data Index: 697392 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1560065 (Python Code)

Max Activating Token Index: 400

Text #10

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4734. Min Act: -0.0001

Data Index: 1372163 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4974. Min Act: -0.0001

Data Index: 1618802 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4782. Min Act: -0.0001

Data Index: 1386895 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4634. Min Act: -0.0000

Data Index: 641888 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4626. Min Act: -0.0001

Data Index: 1465581 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1620607 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4460. Min Act: -0.0001

Data Index: 180468 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4310. Min Act: -0.0001

Data Index: 1389763 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4158. Min Act: -0.0000

Data Index: 626438 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4555. Min Act: -0.0001

Data Index: 787848 (C4 (Web Text))

Max Activating Token Index: 127