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

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

Neuron 5629 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: 2.3550. Min Range: -2.3550

Max Act: 2.3550. Min Act: -0.0000

Data Index: 833617 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 2.3550. Min Range: -2.3550

Max Act: 2.1067. Min Act: -0.0000

Data Index: 1086493 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.8132. Min Act: -0.0000

Data Index: 205471 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.9850. Min Act: -0.0000

Data Index: 1098144 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.6240. Min Act: -0.0000

Data Index: 240236 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.6809. Min Act: -0.0000

Data Index: 229053 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.6777. Min Act: -0.0000

Data Index: 507289 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.5989. Min Act: -0.0000

Data Index: 81868 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.5527. Min Act: -0.0000

Data Index: 552667 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.6141. Min Act: -0.0000

Data Index: 861238 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.6557. Min Act: -0.0000

Data Index: 835352 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.6976. Min Act: -0.0000

Data Index: 747679 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.6874. Min Act: -0.0000

Data Index: 550449 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1103606 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.5648. Min Act: -0.0000

Data Index: 7540 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.4508. Min Act: -0.0000

Data Index: 606134 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.6166. Min Act: -0.0000

Data Index: 957755 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.5154. Min Act: -0.0000

Data Index: 882992 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.5194. Min Act: -0.0000

Data Index: 381290 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 2.3550. Min Range: -2.3550

Max Act: 1.5883. Min Act: -0.0000

Data Index: 399933 (C4 (Web Text))

Max Activating Token Index: 556