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

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

Neuron 724 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2580. Min Range: -3.2580

Max Act: 3.2580. Min Act: -0.0000

Data Index: 1088263 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 3.2580. Min Range: -3.2580

Max Act: 3.0909. Min Act: -0.0000

Data Index: 1413130 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 3.2580. Min Range: -3.2580

Max Act: 3.0582. Min Act: -0.0000

Data Index: 21387 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 3.2580. Min Range: -3.2580

Max Act: 3.1905. Min Act: -0.0000

Data Index: 691567 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 3.2580. Min Range: -3.2580

Max Act: 3.1419. Min Act: -0.0000

Data Index: 1597467 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.9138. Min Act: -0.0000

Data Index: 1560884 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 3.2580. Min Range: -3.2580

Max Act: 3.0361. Min Act: -0.0000

Data Index: 86781 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.7592. Min Act: -0.0000

Data Index: 497113 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 3.2580. Min Range: -3.2580

Max Act: 3.0039. Min Act: -0.0000

Data Index: 1123938 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.9123. Min Act: -0.0000

Data Index: 104431 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.8837. Min Act: -0.0000

Data Index: 1533491 (Python Code)

Max Activating Token Index: 271

Text #11

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.8629. Min Act: -0.0000

Data Index: 393055 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.8162. Min Act: -0.0000

Data Index: 607724 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.8181. Min Act: -0.0000

Data Index: 1089893 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.5080. Min Act: -0.0000

Data Index: 522723 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.6416. Min Act: -0.0000

Data Index: 1084998 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.7781. Min Act: -0.0000

Data Index: 1632953 (Python Code)

Max Activating Token Index: 569

Text #17

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.5911. Min Act: -0.0000

Data Index: 11451 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.8423. Min Act: -0.0000

Data Index: 432525 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 3.2580. Min Range: -3.2580

Max Act: 2.6700. Min Act: -0.0000

Data Index: 905814 (C4 (Web Text))

Max Activating Token Index: 57