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

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

Neuron 1563 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4665. Min Range: -2.4665

Max Act: 2.4665. Min Act: -0.0000

Data Index: 1277470 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 2.4665. Min Range: -2.4665

Max Act: 2.0087. Min Act: -0.0000

Data Index: 400143 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8610. Min Act: -0.0000

Data Index: 1090688 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8595. Min Act: -0.0000

Data Index: 693449 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.9432. Min Act: -0.0000

Data Index: 587819 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.9501. Min Act: -0.0000

Data Index: 23008 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.9172. Min Act: -0.0000

Data Index: 536695 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8228. Min Act: -0.0000

Data Index: 1136488 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8280. Min Act: -0.0000

Data Index: 385542 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8730. Min Act: -0.0000

Data Index: 869543 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8677. Min Act: -0.0000

Data Index: 884326 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8598. Min Act: -0.0000

Data Index: 446543 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8496. Min Act: -0.0000

Data Index: 896575 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8418. Min Act: -0.0000

Data Index: 107468 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8323. Min Act: -0.0000

Data Index: 744500 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8101. Min Act: -0.0000

Data Index: 295773 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.7108. Min Act: -0.0000

Data Index: 248354 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8087. Min Act: -0.0000

Data Index: 967883 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8101. Min Act: -0.0000

Data Index: 688028 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 2.4665. Min Range: -2.4665

Max Act: 1.8956. Min Act: -0.0000

Data Index: 1165987 (C4 (Web Text))

Max Activating Token Index: 298