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

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

Neuron 1478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.8850. Min Act: -0.0001

Data Index: 1319040 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.9086. Min Act: -0.0000

Data Index: 247454 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.6066. Min Act: -0.0000

Data Index: 1329166 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.6047. Min Act: -0.0000

Data Index: 236347 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 3.9086. Min Range: -3.9086

Max Act: 2.8253. Min Act: -0.0001

Data Index: 869559 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.3837. Min Act: -0.0000

Data Index: 226947 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.2491. Min Act: -0.0001

Data Index: 1253604 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.0974. Min Act: -0.0000

Data Index: 26178 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.0786. Min Act: -0.0000

Data Index: 1269423 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.2238. Min Act: -0.0000

Data Index: 289567 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.1811. Min Act: -0.0001

Data Index: 761976 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.1811. Min Act: -0.0000

Data Index: 893719 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.0183. Min Act: -0.0001

Data Index: 675346 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.1279. Min Act: -0.0001

Data Index: 501301 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.0832. Min Act: -0.0000

Data Index: 852890 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 3.9086. Min Range: -3.9086

Max Act: 2.9372. Min Act: -0.0000

Data Index: 562954 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 3.9086. Min Range: -3.9086

Max Act: 2.5395. Min Act: -0.0000

Data Index: 1179354 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.0734. Min Act: -0.0001

Data Index: 476900 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.0162. Min Act: -0.0000

Data Index: 338960 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 3.9086. Min Range: -3.9086

Max Act: 3.0363. Min Act: -0.0000

Data Index: 767552 (C4 (Web Text))

Max Activating Token Index: 951