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

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

Neuron 313 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1579. Min Range: -3.1579

Max Act: 3.1579. Min Act: -0.0000

Data Index: 615242 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.5701. Min Act: -0.0000

Data Index: 957520 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.2981. Min Act: -0.0000

Data Index: 454609 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.1677. Min Act: 0.0000

Data Index: 1116882 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.2494. Min Act: -0.0000

Data Index: 850356 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.3442. Min Act: -0.0000

Data Index: 525749 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.0540. Min Act: 0.0000

Data Index: 1175224 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.1579. Min Range: -3.1579

Max Act: 2.0172. Min Act: 0.0000

Data Index: 728684 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.9989. Min Act: -0.0000

Data Index: 94529 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.8305. Min Act: -0.0000

Data Index: 1282288 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.9109. Min Act: -0.0000

Data Index: 242932 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.7166. Min Act: -0.0000

Data Index: 1331553 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.7901. Min Act: 0.0000

Data Index: 1158532 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.7829. Min Act: -0.0000

Data Index: 1281312 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.7824. Min Act: -0.0000

Data Index: 988115 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.7653. Min Act: -0.0000

Data Index: 631419 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.7487. Min Act: -0.0000

Data Index: 146842 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1108091 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.6010. Min Act: -0.0000

Data Index: 1292048 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 3.1579. Min Range: -3.1579

Max Act: 1.6939. Min Act: -0.0000

Data Index: 649811 (C4 (Web Text))

Max Activating Token Index: 963