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

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

Neuron 2745 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.4431. Min Act: -0.0000

Data Index: 317717 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.1265. Min Act: -0.0000

Data Index: 553202 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0784. Min Act: -0.0000

Data Index: 885679 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0670. Min Act: -0.0000

Data Index: 294009 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 1.4431. Min Range: -1.4431

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1203967 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9810. Min Act: -0.0000

Data Index: 64651 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9674. Min Act: -0.0000

Data Index: 990872 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8999. Min Act: -0.0000

Data Index: 800865 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9451. Min Act: -0.0000

Data Index: 95115 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9486. Min Act: -0.0000

Data Index: 53084 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9063. Min Act: -0.0001

Data Index: 1269388 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8424. Min Act: -0.0000

Data Index: 152647 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9030. Min Act: -0.0001

Data Index: 1097512 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1108969 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8618. Min Act: -0.0000

Data Index: 993534 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9040. Min Act: -0.0000

Data Index: 89688 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1299406 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.9240. Min Act: -0.0000

Data Index: 202152 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8373. Min Act: -0.0001

Data Index: 1128172 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.4431. Min Range: -1.4431

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1171223 (C4 (Web Text))

Max Activating Token Index: 458