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

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

Neuron 1741 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5422. Min Range: -3.5422

Max Act: 3.2885. Min Act: -0.0000

Data Index: 211579 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 3.5422. Min Range: -3.5422

Max Act: 3.5422. Min Act: -0.0000

Data Index: 630473 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 3.5422. Min Range: -3.5422

Max Act: 3.2832. Min Act: -0.0000

Data Index: 820431 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 3.5422. Min Range: -3.5422

Max Act: 3.1450. Min Act: -0.0000

Data Index: 754168 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 3.5422. Min Range: -3.5422

Max Act: 3.0842. Min Act: -0.0000

Data Index: 303833 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.7920. Min Act: -0.0000

Data Index: 253313 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.7894. Min Act: -0.0000

Data Index: 1074177 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.7350. Min Act: -0.0000

Data Index: 436463 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.6201. Min Act: -0.0000

Data Index: 882172 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.4710. Min Act: -0.0000

Data Index: 322686 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.4870. Min Act: -0.0000

Data Index: 971380 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.5878. Min Act: -0.0000

Data Index: 455667 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.4186. Min Act: -0.0000

Data Index: 687844 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.2855. Min Act: -0.0000

Data Index: 668014 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.5321. Min Act: -0.0000

Data Index: 1263575 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.4596. Min Act: -0.0000

Data Index: 1134663 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.4492. Min Act: -0.0000

Data Index: 1533029 (Python Code)

Max Activating Token Index: 580

Text #17

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.2999. Min Act: -0.0000

Data Index: 1473559 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.3027. Min Act: -0.0000

Data Index: 29886 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 3.5422. Min Range: -3.5422

Max Act: 2.1786. Min Act: -0.0000

Data Index: 1204035 (C4 (Web Text))

Max Activating Token Index: 560