Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3487 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1512. Min Range: -4.1512

Max Act: 4.1512. Min Act: -0.0001

Data Index: 553728 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 4.1512. Min Range: -4.1512

Max Act: 3.4270. Min Act: -0.0001

Data Index: 45448 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 4.1512. Min Range: -4.1512

Max Act: 3.5742. Min Act: -0.0001

Data Index: 890841 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 4.1512. Min Range: -4.1512

Max Act: 3.3567. Min Act: -0.0000

Data Index: 1147415 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 4.1512. Min Range: -4.1512

Max Act: 3.4721. Min Act: -0.0001

Data Index: 544551 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 4.1512. Min Range: -4.1512

Max Act: 3.1617. Min Act: -0.0001

Data Index: 947590 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 4.1512. Min Range: -4.1512

Max Act: 3.1932. Min Act: -0.0001

Data Index: 144737 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 4.1512. Min Range: -4.1512

Max Act: 3.6119. Min Act: -0.0001

Data Index: 464902 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.9584. Min Act: -0.0000

Data Index: 906429 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 4.1512. Min Range: -4.1512

Max Act: 3.0498. Min Act: -0.0001

Data Index: 663375 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.9217. Min Act: -0.0000

Data Index: 782327 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.8794. Min Act: -0.0001

Data Index: 121470 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.9777. Min Act: -0.0001

Data Index: 642774 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.5600. Min Act: -0.0001

Data Index: 387666 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.6541. Min Act: -0.0001

Data Index: 378397 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.9093. Min Act: -0.0000

Data Index: 388830 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.8659. Min Act: -0.0000

Data Index: 862712 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.7303. Min Act: -0.0001

Data Index: 335692 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.7042. Min Act: -0.0000

Data Index: 7103 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 4.1512. Min Range: -4.1512

Max Act: 2.6876. Min Act: -0.0001

Data Index: 151134 (C4 (Web Text))

Max Activating Token Index: 809