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

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

Neuron 5129 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7674. Min Range: -2.7674

Max Act: 2.7674. Min Act: -0.0000

Data Index: 1343308 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 2.7674. Min Range: -2.7674

Max Act: 2.7451. Min Act: -0.0000

Data Index: 898427 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 2.7674. Min Range: -2.7674

Max Act: 2.5451. Min Act: -0.0000

Data Index: 49817 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 2.7674. Min Range: -2.7674

Max Act: 2.4156. Min Act: -0.0000

Data Index: 409355 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 2.7674. Min Range: -2.7674

Max Act: 2.3411. Min Act: -0.0000

Data Index: 136810 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 2.7674. Min Range: -2.7674

Max Act: 2.3952. Min Act: -0.0000

Data Index: 473616 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 2.7674. Min Range: -2.7674

Max Act: 2.2879. Min Act: -0.0000

Data Index: 526075 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.8487. Min Act: -0.0000

Data Index: 618307 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.8486. Min Act: -0.0000

Data Index: 1126404 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.8420. Min Act: -0.0000

Data Index: 951730 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.9463. Min Act: -0.0000

Data Index: 1139741 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.8555. Min Act: -0.0000

Data Index: 1271507 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.8098. Min Act: -0.0000

Data Index: 734494 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.7864. Min Act: -0.0000

Data Index: 1335635 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.7878. Min Act: -0.0000

Data Index: 12806 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.7770. Min Act: -0.0000

Data Index: 950572 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.7184. Min Act: -0.0000

Data Index: 1113322 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.8161. Min Act: -0.0000

Data Index: 1243084 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.8146. Min Act: -0.0000

Data Index: 40109 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 2.7674. Min Range: -2.7674

Max Act: 1.6990. Min Act: -0.0000

Data Index: 393424 (C4 (Web Text))

Max Activating Token Index: 686