Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 574 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1058. Min Act: -0.0001

Data Index: 666331 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0734. Min Act: -0.0001

Data Index: 107976 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0748. Min Act: -0.0001

Data Index: 909651 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0708. Min Act: -0.0001

Data Index: 87272 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0709. Min Act: -0.0001

Data Index: 196899 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0702. Min Act: -0.0001

Data Index: 849850 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1279697 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0683. Min Act: -0.0001

Data Index: 993766 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0680. Min Act: -0.0001

Data Index: 693175 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1280001 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1147734 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0667. Min Act: -0.0001

Data Index: 400303 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0658. Min Act: -0.0001

Data Index: 209306 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0656. Min Act: -0.0001

Data Index: 514177 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0652. Min Act: -0.0001

Data Index: 373186 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1193269 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0651. Min Act: -0.0001

Data Index: 860316 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1154705 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0644. Min Act: -0.0001

Data Index: 4786 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0659. Min Act: -0.0001

Data Index: 388815 (C4 (Web Text))

Max Activating Token Index: 371