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

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

Neuron 4388 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1460501 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1369792 (Python Code)

Max Activating Token Index: 422

Text #2

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1454205 (Python Code)

Max Activating Token Index: 441

Text #3

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.4669. Min Act: -0.0000

Data Index: 601867 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1489937 (Python Code)

Max Activating Token Index: 611

Text #5

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1450112 (Python Code)

Max Activating Token Index: 927

Text #6

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.4344. Min Act: -0.0000

Data Index: 618577 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.4132. Min Act: -0.0000

Data Index: 311799 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.4135. Min Act: -0.0000

Data Index: 127566 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.4194. Min Act: -0.0000

Data Index: 963002 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3851. Min Act: -0.0000

Data Index: 554547 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3975. Min Act: -0.0000

Data Index: 577997 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3718. Min Act: -0.0000

Data Index: 625260 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1553479 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1333079 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3663. Min Act: -0.0000

Data Index: 308263 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3342. Min Act: -0.0000

Data Index: 638524 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1350215 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3542. Min Act: -0.0000

Data Index: 522660 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.6148. Min Range: -0.6148

Max Act: 0.3305. Min Act: -0.0000

Data Index: 403436 (C4 (Web Text))

Max Activating Token Index: 756