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

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

Neuron 5818 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.4803. Min Act: -0.0002

Data Index: 601493 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.3413. Min Act: -0.0002

Data Index: 382298 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.3688. Min Act: -0.0002

Data Index: 838991 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.3158. Min Act: -0.0002

Data Index: 814690 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.2421. Min Act: -0.0002

Data Index: 229804 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.2369. Min Act: -0.0002

Data Index: 907580 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1841. Min Act: -0.0002

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.2554. Min Act: -0.0002

Data Index: 903736 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1634. Min Act: -0.0002

Data Index: 896480 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1435. Min Act: -0.0002

Data Index: 158127 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.2634. Min Act: -0.0003

Data Index: 458752 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1431. Min Act: -0.0002

Data Index: 339439 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1904. Min Act: -0.0002

Data Index: 1039860 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1380. Min Act: -0.0002

Data Index: 815486 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1889. Min Act: -0.0003

Data Index: 1139571 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1624. Min Act: -0.0002

Data Index: 1145024 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.2083. Min Act: -0.0002

Data Index: 589603 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1380. Min Act: -0.0002

Data Index: 541559 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1102. Min Act: -0.0002

Data Index: 136545 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 2.4803. Min Range: -2.4803

Max Act: 2.1233. Min Act: -0.0002

Data Index: 1301572 (C4 (Web Text))

Max Activating Token Index: 97