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

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

Neuron 985 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: 4.1817. Min Range: -4.1817

Max Act: 4.1817. Min Act: -0.0000

Data Index: 1146723 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 4.1817. Min Range: -4.1817

Max Act: 3.4665. Min Act: -0.0000

Data Index: 1058605 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 4.1817. Min Range: -4.1817

Max Act: 3.3350. Min Act: -0.0000

Data Index: 1152446 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 4.1817. Min Range: -4.1817

Max Act: 3.7721. Min Act: -0.0000

Data Index: 533651 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.9311. Min Act: -0.0000

Data Index: 1057484 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 4.1817. Min Range: -4.1817

Max Act: 3.0008. Min Act: -0.0000

Data Index: 520071 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.7996. Min Act: -0.0000

Data Index: 740827 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.9193. Min Act: -0.0000

Data Index: 271062 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.7612. Min Act: -0.0000

Data Index: 488034 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.9057. Min Act: -0.0000

Data Index: 1127935 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.7445. Min Act: -0.0000

Data Index: 580564 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.8519. Min Act: -0.0000

Data Index: 747484 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.8543. Min Act: -0.0000

Data Index: 95979 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.7129. Min Act: -0.0000

Data Index: 858596 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.7980. Min Act: -0.0000

Data Index: 757681 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.7285. Min Act: -0.0000

Data Index: 589783 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.8138. Min Act: -0.0000

Data Index: 1154712 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.6456. Min Act: -0.0000

Data Index: 684327 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.5159. Min Act: -0.0000

Data Index: 614429 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 4.1817. Min Range: -4.1817

Max Act: 2.6285. Min Act: -0.0000

Data Index: 1155118 (C4 (Web Text))

Max Activating Token Index: 675