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

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

Neuron 661 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.7873. Min Act: -0.0001

Data Index: 617302 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.8366. Min Act: -0.0001

Data Index: 950587 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.8643. Min Act: -0.0001

Data Index: 529013 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.6141. Min Act: -0.0001

Data Index: 677932 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.6693. Min Act: -0.0001

Data Index: 1041669 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.4458. Min Act: -0.0001

Data Index: 1075186 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.7394. Min Act: -0.0001

Data Index: 535707 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.5962. Min Act: -0.0001

Data Index: 123437 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.5988. Min Act: -0.0001

Data Index: 1308698 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.5273. Min Act: -0.0001

Data Index: 1270955 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.6076. Min Act: -0.0001

Data Index: 148831 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.6179. Min Act: -0.0001

Data Index: 925439 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.7463. Min Act: -0.0001

Data Index: 306684 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.5844. Min Act: -0.0001

Data Index: 1337130 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.4729. Min Act: -0.0001

Data Index: 339765 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.5739. Min Act: -0.0001

Data Index: 1332134 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.5243. Min Act: -0.0001

Data Index: 1145774 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.5088. Min Act: -0.0001

Data Index: 929680 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.3867. Min Act: -0.0001

Data Index: 777767 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 1.8643. Min Range: -1.8643

Max Act: 1.5453. Min Act: -0.0001

Data Index: 104908 (C4 (Web Text))

Max Activating Token Index: 727