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

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

Neuron 3086 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1092956 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2422. Min Act: -0.0000

Data Index: 998634 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2467. Min Act: -0.0000

Data Index: 822823 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2355. Min Act: -0.0000

Data Index: 163114 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1223829 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2284. Min Act: -0.0000

Data Index: 245224 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1120325 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2399. Min Act: -0.0000

Data Index: 729940 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2325. Min Act: -0.0000

Data Index: 928042 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2289. Min Act: -0.0000

Data Index: 81926 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2360. Min Act: -0.0000

Data Index: 593231 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2267. Min Act: -0.0000

Data Index: 926911 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1147038 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2249. Min Act: -0.0000

Data Index: 908718 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2314. Min Act: -0.0000

Data Index: 518558 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.1917. Min Act: -0.0000

Data Index: 698929 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2104. Min Act: -0.0000

Data Index: 863040 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2112. Min Act: -0.0000

Data Index: 258773 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2199. Min Act: -0.0000

Data Index: 67951 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1299167 (C4 (Web Text))

Max Activating Token Index: 9