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

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

Neuron 3458 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.2790. Min Act: 0.0000

Data Index: 1127754 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1055890 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.1909. Min Act: -0.0000

Data Index: 130687 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.1763. Min Act: -0.0000

Data Index: 969115 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.1458. Min Act: -0.0000

Data Index: 572038 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.0148. Min Act: -0.0000

Data Index: 420044 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1248162 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.0884. Min Act: -0.0000

Data Index: 448221 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.0278. Min Act: -0.0000

Data Index: 838010 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.0442. Min Act: -0.0000

Data Index: 760909 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9953. Min Act: -0.0000

Data Index: 190202 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1040278 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9982. Min Act: -0.0000

Data Index: 642638 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9530. Min Act: -0.0000

Data Index: 146597 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8437. Min Act: -0.0000

Data Index: 976038 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9672. Min Act: -0.0000

Data Index: 172729 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9323. Min Act: -0.0000

Data Index: 271517 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9082. Min Act: -0.0000

Data Index: 455498 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1280694 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9179. Min Act: -0.0000

Data Index: 158491 (C4 (Web Text))

Max Activating Token Index: 812