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

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

Neuron 1428 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: 3.6278. Min Range: -3.6278

Max Act: 3.6278. Min Act: -0.0000

Data Index: 619198 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.4262. Min Act: -0.0000

Data Index: 877751 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.1331. Min Act: -0.0000

Data Index: 450451 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.0322. Min Act: -0.0000

Data Index: 36459 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.6420. Min Act: -0.0000

Data Index: 327987 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.9516. Min Act: -0.0000

Data Index: 685383 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.4633. Min Act: -0.0000

Data Index: 132099 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.7168. Min Act: -0.0000

Data Index: 181126 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.6946. Min Act: -0.0000

Data Index: 1046498 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.4408. Min Act: -0.0000

Data Index: 1301399 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.5453. Min Act: -0.0000

Data Index: 845104 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.5486. Min Act: -0.0000

Data Index: 1216240 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.3772. Min Act: -0.0000

Data Index: 1066981 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.3496. Min Act: -0.0000

Data Index: 656036 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.3501. Min Act: -0.0000

Data Index: 824247 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.1803. Min Act: -0.0000

Data Index: 7849 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.0244. Min Act: -0.0000

Data Index: 532571 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.3565. Min Act: -0.0000

Data Index: 247709 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.0988. Min Act: -0.0000

Data Index: 638676 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 3.6278. Min Range: -3.6278

Max Act: 2.0902. Min Act: -0.0000

Data Index: 933434 (C4 (Web Text))

Max Activating Token Index: 142