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

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

Neuron 528 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.6145. Min Act: -0.0002

Data Index: 645071 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5943. Min Act: -0.0002

Data Index: 701921 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.6161. Min Act: -0.0002

Data Index: 357818 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.6085. Min Act: -0.0002

Data Index: 48995 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5947. Min Act: -0.0002

Data Index: 98981 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5591. Min Act: -0.0002

Data Index: 832889 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5633. Min Act: -0.0002

Data Index: 1198253 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4933. Min Act: -0.0002

Data Index: 222450 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4367. Min Act: -0.0002

Data Index: 122257 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4088. Min Act: -0.0002

Data Index: 392016 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4188. Min Act: -0.0001

Data Index: 1319430 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4216. Min Act: -0.0001

Data Index: 713833 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3847. Min Act: -0.0002

Data Index: 633292 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3996. Min Act: -0.0001

Data Index: 925102 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3752. Min Act: -0.0001

Data Index: 1061994 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3736. Min Act: -0.0001

Data Index: 1248788 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3586. Min Act: -0.0002

Data Index: 571717 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3520. Min Act: -0.0001

Data Index: 1235087 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3852. Min Act: -0.0002

Data Index: 354572 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3723. Min Act: -0.0002

Data Index: 269048 (C4 (Web Text))

Max Activating Token Index: 15