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

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

Neuron 5182 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: 2.4896. Min Range: -2.4896

Max Act: 2.4896. Min Act: -0.0000

Data Index: 486475 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 2.4896. Min Range: -2.4896

Max Act: 2.2497. Min Act: -0.0000

Data Index: 380919 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 2.4896. Min Range: -2.4896

Max Act: 2.3642. Min Act: -0.0001

Data Index: 433198 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 2.4896. Min Range: -2.4896

Max Act: 2.3256. Min Act: -0.0000

Data Index: 670684 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 2.4896. Min Range: -2.4896

Max Act: 2.2739. Min Act: -0.0000

Data Index: 618790 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 2.4896. Min Range: -2.4896

Max Act: 2.2642. Min Act: -0.0000

Data Index: 965246 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 2.4896. Min Range: -2.4896

Max Act: 2.3162. Min Act: -0.0000

Data Index: 1113489 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 2.4896. Min Range: -2.4896

Max Act: 2.0644. Min Act: -0.0000

Data Index: 235192 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 2.4896. Min Range: -2.4896

Max Act: 2.1014. Min Act: -0.0000

Data Index: 1161909 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.8701. Min Act: -0.0000

Data Index: 1298243 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.9657. Min Act: -0.0001

Data Index: 630422 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.8318. Min Act: -0.0000

Data Index: 1180864 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.7741. Min Act: -0.0000

Data Index: 596356 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.7296. Min Act: -0.0000

Data Index: 280811 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.7118. Min Act: -0.0000

Data Index: 807158 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.7060. Min Act: -0.0000

Data Index: 125673 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.7933. Min Act: -0.0000

Data Index: 820096 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.6588. Min Act: -0.0001

Data Index: 675309 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.6430. Min Act: -0.0001

Data Index: 1198757 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 2.4896. Min Range: -2.4896

Max Act: 1.7962. Min Act: -0.0001

Data Index: 400138 (C4 (Web Text))

Max Activating Token Index: 355