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

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

Neuron 807 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.1001. Min Act: -0.0000

Data Index: 808655 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.2053. Min Act: -0.0000

Data Index: 804765 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.3088. Min Act: -0.0000

Data Index: 949913 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.1742. Min Act: -0.0000

Data Index: 759368 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.1580. Min Act: -0.0000

Data Index: 707038 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.0387. Min Act: -0.0000

Data Index: 734340 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 2.3088. Min Range: -2.3088

Max Act: 1.8864. Min Act: -0.0000

Data Index: 602881 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 2.3088. Min Range: -2.3088

Max Act: 1.9358. Min Act: -0.0000

Data Index: 1357574 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.1471. Min Act: -0.0000

Data Index: 1255443 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 2.3088. Min Range: -2.3088

Max Act: 1.9281. Min Act: -0.0000

Data Index: 29020 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 2.3088. Min Range: -2.3088

Max Act: 1.9276. Min Act: -0.0000

Data Index: 931373 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 2.3088. Min Range: -2.3088

Max Act: 1.9874. Min Act: -0.0000

Data Index: 1244586 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.0160. Min Act: -0.0000

Data Index: 507139 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 2.3088. Min Range: -2.3088

Max Act: 1.9509. Min Act: -0.0000

Data Index: 1307234 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.1103. Min Act: -0.0000

Data Index: 118578 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.0349. Min Act: -0.0000

Data Index: 178486 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.0794. Min Act: -0.0000

Data Index: 9544 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 2.3088. Min Range: -2.3088

Max Act: 2.0393. Min Act: -0.0000

Data Index: 461211 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 2.3088. Min Range: -2.3088

Max Act: 1.9350. Min Act: -0.0000

Data Index: 640271 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 2.3088. Min Range: -2.3088

Max Act: 1.9217. Min Act: -0.0000

Data Index: 679541 (C4 (Web Text))

Max Activating Token Index: 252