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

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

Neuron 4038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5487. Min Range: -1.5487

Max Act: 1.5487. Min Act: -0.0000

Data Index: 924841 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.5487. Min Range: -1.5487

Max Act: 1.4040. Min Act: -0.0000

Data Index: 440235 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.5487. Min Range: -1.5487

Max Act: 1.2550. Min Act: -0.0000

Data Index: 666187 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 1.5487. Min Range: -1.5487

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1353559 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.9459. Min Act: -0.0001

Data Index: 1138163 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1283188 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.8651. Min Act: -0.0001

Data Index: 664140 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.5487. Min Range: -1.5487

Max Act: 1.0357. Min Act: -0.0000

Data Index: 31298 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1180116 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1195308 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.8664. Min Act: -0.0000

Data Index: 14939 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.8328. Min Act: -0.0000

Data Index: 447018 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.7518. Min Act: -0.0000

Data Index: 24687 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.7725. Min Act: -0.0001

Data Index: 970551 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.7371. Min Act: -0.0000

Data Index: 84808 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.7131. Min Act: -0.0000

Data Index: 546958 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.7078. Min Act: -0.0001

Data Index: 647012 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.6980. Min Act: -0.0000

Data Index: 968572 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1126671 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.5487. Min Range: -1.5487

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1136322 (C4 (Web Text))

Max Activating Token Index: 418