Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1301 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.5018. Min Act: -0.0002

Data Index: 1600901 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.5083. Min Act: -0.0001

Data Index: 513778 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4451. Min Act: -0.0001

Data Index: 1444160 (Python Code)

Max Activating Token Index: 812

Text #3

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4118. Min Act: -0.0001

Data Index: 1651603 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1459000 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4367. Min Act: -0.0001

Data Index: 1627752 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4130. Min Act: -0.0001

Data Index: 998570 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4315. Min Act: -0.0001

Data Index: 159918 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4348. Min Act: -0.0001

Data Index: 1383100 (Python Code)

Max Activating Token Index: 403

Text #9

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.3924. Min Act: -0.0001

Data Index: 133559 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4364. Min Act: -0.0001

Data Index: 569522 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4195. Min Act: -0.0002

Data Index: 373334 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4260. Min Act: -0.0002

Data Index: 220201 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4254. Min Act: -0.0001

Data Index: 1440083 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4249. Min Act: -0.0002

Data Index: 919927 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.3714. Min Act: -0.0001

Data Index: 1363487 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4078. Min Act: -0.0001

Data Index: 1236498 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4102. Min Act: -0.0001

Data Index: 553758 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4303. Min Act: -0.0001

Data Index: 1319792 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.5083. Min Range: -0.5083

Max Act: 0.4154. Min Act: -0.0001

Data Index: 852309 (C4 (Web Text))

Max Activating Token Index: 828