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

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

Neuron 3259 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: 0.8662. Min Range: -0.8662

Max Act: 0.8662. Min Act: -0.0001

Data Index: 863412 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.8077. Min Act: -0.0001

Data Index: 1262257 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7025. Min Act: -0.0001

Data Index: 646900 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7215. Min Act: -0.0001

Data Index: 1176056 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6834. Min Act: -0.0001

Data Index: 1171932 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7480. Min Act: -0.0001

Data Index: 1267503 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7524. Min Act: -0.0001

Data Index: 755730 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7266. Min Act: -0.0001

Data Index: 794078 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7074. Min Act: -0.0001

Data Index: 1133157 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7373. Min Act: -0.0001

Data Index: 885565 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6657. Min Act: -0.0001

Data Index: 285450 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6867. Min Act: -0.0001

Data Index: 792216 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6493. Min Act: -0.0001

Data Index: 1089569 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1243605 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6323. Min Act: -0.0001

Data Index: 437383 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7016. Min Act: -0.0001

Data Index: 958845 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6514. Min Act: -0.0001

Data Index: 1186411 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6815. Min Act: -0.0001

Data Index: 547361 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6003. Min Act: -0.0001

Data Index: 711876 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6738. Min Act: -0.0001

Data Index: 1108539 (C4 (Web Text))

Max Activating Token Index: 607