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

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

Neuron 3056 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.8500. Min Act: -0.0000

Data Index: 142876 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.8353. Min Act: -0.0000

Data Index: 39709 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.5958. Min Act: -0.0000

Data Index: 849412 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.5637. Min Act: -0.0000

Data Index: 652599 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.5516. Min Act: -0.0000

Data Index: 125526 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.5467. Min Act: -0.0000

Data Index: 810369 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.5259. Min Act: -0.0000

Data Index: 514054 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1002999 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1250547 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.3711. Min Act: -0.0000

Data Index: 17497 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.3344. Min Act: -0.0000

Data Index: 1284619 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.3506. Min Act: -0.0000

Data Index: 232172 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.3232. Min Act: -0.0000

Data Index: 52388 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.1904. Min Act: -0.0000

Data Index: 764444 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.3422. Min Act: -0.0000

Data Index: 1309736 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.2765. Min Act: -0.0000

Data Index: 798239 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1132176 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.1624. Min Act: -0.0000

Data Index: 839526 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.2764. Min Act: -0.0000

Data Index: 80532 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.8500. Min Range: -1.8500

Max Act: 1.2863. Min Act: -0.0000

Data Index: 227967 (C4 (Web Text))

Max Activating Token Index: 818