Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3475 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4910. Min Range: -1.4910

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1416598 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 1.4910. Min Range: -1.4910

Max Act: 1.1037. Min Act: -0.0000

Data Index: 661030 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 1.4910. Min Range: -1.4910

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1618539 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 1.4910. Min Range: -1.4910

Max Act: 1.0599. Min Act: -0.0001

Data Index: 1476942 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 1.4910. Min Range: -1.4910

Max Act: 1.0714. Min Act: -0.0000

Data Index: 837666 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 1.4910. Min Range: -1.4910

Max Act: 1.1058. Min Act: -0.0000

Data Index: 17915 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.8699. Min Act: -0.0000

Data Index: 704208 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.8932. Min Act: -0.0001

Data Index: 585620 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.9555. Min Act: -0.0000

Data Index: 641356 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1168623 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.4910. Min Range: -1.4910

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1322460 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.9722. Min Act: -0.0001

Data Index: 1335431 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.9643. Min Act: -0.0000

Data Index: 637473 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.9123. Min Act: -0.0000

Data Index: 11759 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.8390. Min Act: -0.0000

Data Index: 684873 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1018820 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.8311. Min Act: -0.0000

Data Index: 142223 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.8487. Min Act: -0.0000

Data Index: 852640 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1279111 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.4910. Min Range: -1.4910

Max Act: 0.8727. Min Act: -0.0000

Data Index: 721783 (C4 (Web Text))

Max Activating Token Index: 482