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

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

Neuron 2503 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2781. Min Act: -0.0000

Data Index: 17958 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1203530 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2536. Min Act: -0.0000

Data Index: 807149 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2377. Min Act: -0.0001

Data Index: 69149 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2573. Min Act: -0.0000

Data Index: 342241 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2394. Min Act: -0.0001

Data Index: 625887 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2356. Min Act: -0.0001

Data Index: 1251485 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2293. Min Act: -0.0000

Data Index: 64642 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2438. Min Act: -0.0000

Data Index: 699000 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2329. Min Act: -0.0001

Data Index: 1357806 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2283. Min Act: -0.0001

Data Index: 140439 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2196. Min Act: -0.0001

Data Index: 71620 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2155. Min Act: -0.0000

Data Index: 797781 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2157. Min Act: -0.0001

Data Index: 80774 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2102. Min Act: 0.0000

Data Index: 950130 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1328717 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1102012 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2276. Min Act: -0.0001

Data Index: 612335 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1328820 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2092. Min Act: -0.0001

Data Index: 465562 (C4 (Web Text))

Max Activating Token Index: 568