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

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

Neuron 3917 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0782. Min Range: -3.0782

Max Act: 3.0782. Min Act: -0.0000

Data Index: 677359 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.8834. Min Act: -0.0000

Data Index: 535487 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.7411. Min Act: -0.0000

Data Index: 1248782 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.3517. Min Act: -0.0000

Data Index: 1192937 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.4487. Min Act: -0.0000

Data Index: 1047340 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.3788. Min Act: -0.0000

Data Index: 620010 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.5192. Min Act: -0.0000

Data Index: 187397 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.4167. Min Act: -0.0000

Data Index: 1049698 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.3485. Min Act: -0.0000

Data Index: 659140 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.3414. Min Act: -0.0000

Data Index: 430672 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.2146. Min Act: -0.0000

Data Index: 928492 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.1949. Min Act: -0.0000

Data Index: 183616 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.0586. Min Act: -0.0000

Data Index: 87352 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.4567. Min Act: -0.0000

Data Index: 493218 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.2764. Min Act: -0.0000

Data Index: 684964 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.1366. Min Act: -0.0000

Data Index: 651210 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.2467. Min Act: -0.0000

Data Index: 1042624 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.1125. Min Act: -0.0000

Data Index: 615771 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.1953. Min Act: -0.0000

Data Index: 911390 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 3.0782. Min Range: -3.0782

Max Act: 2.1606. Min Act: -0.0000

Data Index: 461426 (C4 (Web Text))

Max Activating Token Index: 351