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

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

Neuron 3758 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8844. Min Act: -0.0001

Data Index: 797543 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9278. Min Act: -0.0001

Data Index: 90388 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9084. Min Act: -0.0001

Data Index: 899149 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8944. Min Act: -0.0001

Data Index: 533932 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8431. Min Act: -0.0001

Data Index: 922575 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1348756 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1093956 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8167. Min Act: -0.0001

Data Index: 878964 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7447. Min Act: -0.0001

Data Index: 273370 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8082. Min Act: -0.0001

Data Index: 246049 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7772. Min Act: -0.0001

Data Index: 262763 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7299. Min Act: -0.0001

Data Index: 412305 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8038. Min Act: -0.0001

Data Index: 806811 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7890. Min Act: -0.0001

Data Index: 301485 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7526. Min Act: -0.0001

Data Index: 1116212 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7362. Min Act: -0.0001

Data Index: 155411 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7555. Min Act: -0.0001

Data Index: 1304631 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8031. Min Act: -0.0001

Data Index: 699047 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7309. Min Act: -0.0001

Data Index: 1327838 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7767. Min Act: -0.0001

Data Index: 1157476 (C4 (Web Text))

Max Activating Token Index: 304