Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2678 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2414. Min Range: -1.2414

Max Act: 1.2414. Min Act: -0.0001

Data Index: 183480 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.2414. Min Range: -1.2414

Max Act: 1.0523. Min Act: -0.0001

Data Index: 935812 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.9315. Min Act: -0.0001

Data Index: 703922 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.9839. Min Act: -0.0001

Data Index: 986960 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.9800. Min Act: -0.0001

Data Index: 348742 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.8374. Min Act: -0.0001

Data Index: 1031306 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.9423. Min Act: -0.0001

Data Index: 690857 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.9526. Min Act: -0.0001

Data Index: 229288 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.7067. Min Act: -0.0001

Data Index: 124016 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.8410. Min Act: -0.0001

Data Index: 1359652 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.8071. Min Act: -0.0001

Data Index: 513592 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.8168. Min Act: -0.0001

Data Index: 56877 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.8903. Min Act: -0.0001

Data Index: 936230 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.7770. Min Act: -0.0001

Data Index: 225916 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.8659. Min Act: -0.0001

Data Index: 397636 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.6585. Min Act: -0.0001

Data Index: 660593 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.6698. Min Act: -0.0001

Data Index: 538221 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.6874. Min Act: -0.0001

Data Index: 925684 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.7267. Min Act: -0.0001

Data Index: 810832 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 1.2414. Min Range: -1.2414

Max Act: 0.7482. Min Act: -0.0001

Data Index: 95169 (C4 (Web Text))

Max Activating Token Index: 504