Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1824 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 2.6445. Min Range: -2.6445

Max Act: 2.3853. Min Act: -0.0001

Data Index: 232990 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 2.6445. Min Range: -2.6445

Max Act: 2.6445. Min Act: -0.0001

Data Index: 180436 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 2.6445. Min Range: -2.6445

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1184663 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.6445. Min Range: -2.6445

Max Act: 1.1682. Min Act: -0.0000

Data Index: 315196 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.8335. Min Act: -0.0001

Data Index: 114103 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.9398. Min Act: -0.0001

Data Index: 837569 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.7993. Min Act: -0.0001

Data Index: 1181751 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.8399. Min Act: -0.0000

Data Index: 154524 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.3602. Min Act: -0.0001

Data Index: 82826 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.7817. Min Act: -0.0001

Data Index: 381174 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.6699. Min Act: -0.0001

Data Index: 659460 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.6095. Min Act: -0.0000

Data Index: 322230 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.5953. Min Act: -0.0001

Data Index: 441262 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.6355. Min Act: -0.0000

Data Index: 351006 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1064700 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.5110. Min Act: -0.0000

Data Index: 333926 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.4610. Min Act: -0.0000

Data Index: 216490 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.4193. Min Act: -0.0001

Data Index: 932164 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.5201. Min Act: -0.0001

Data Index: 753485 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 2.6445. Min Range: -2.6445

Max Act: 0.4481. Min Act: -0.0001

Data Index: 387276 (C4 (Web Text))

Max Activating Token Index: 6