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

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

Neuron 3706 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6386. Min Range: -4.6386

Max Act: 4.6386. Min Act: -0.0000

Data Index: 642417 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 4.6386. Min Range: -4.6386

Max Act: 4.2973. Min Act: -0.0000

Data Index: 498683 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.9125. Min Act: -0.0000

Data Index: 333875 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.9669. Min Act: -0.0000

Data Index: 1341993 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.9616. Min Act: -0.0000

Data Index: 668068 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.5408. Min Act: -0.0000

Data Index: 549802 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.7360. Min Act: -0.0000

Data Index: 1229948 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.6256. Min Act: -0.0000

Data Index: 660932 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.7657. Min Act: -0.0000

Data Index: 973699 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.4209. Min Act: -0.0000

Data Index: 786622 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.4010. Min Act: -0.0000

Data Index: 1321395 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.6822. Min Act: -0.0000

Data Index: 1161998 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.5648. Min Act: -0.0000

Data Index: 360430 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.4695. Min Act: -0.0000

Data Index: 1125435 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.6305. Min Act: -0.0000

Data Index: 515480 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.1728. Min Act: -0.0000

Data Index: 834006 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.2041. Min Act: -0.0000

Data Index: 692583 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 4.6386. Min Range: -4.6386

Max Act: 2.8249. Min Act: -0.0000

Data Index: 1126895 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.3461. Min Act: -0.0000

Data Index: 1099335 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 4.6386. Min Range: -4.6386

Max Act: 3.1725. Min Act: -0.0000

Data Index: 610841 (C4 (Web Text))

Max Activating Token Index: 77