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

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

Neuron 2354 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.5647. Min Act: -0.0001

Data Index: 775507 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.5531. Min Act: -0.0001

Data Index: 370023 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.5035. Min Act: -0.0000

Data Index: 690879 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.5272. Min Act: -0.0001

Data Index: 1268201 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.5203. Min Act: -0.0001

Data Index: 143518 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4774. Min Act: -0.0000

Data Index: 962870 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4757. Min Act: -0.0000

Data Index: 284914 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4795. Min Act: -0.0000

Data Index: 156604 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4715. Min Act: -0.0000

Data Index: 553701 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4702. Min Act: -0.0001

Data Index: 889127 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4547. Min Act: -0.0000

Data Index: 226406 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1204740 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4704. Min Act: -0.0000

Data Index: 676124 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4381. Min Act: -0.0001

Data Index: 982884 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1085812 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4556. Min Act: -0.0000

Data Index: 677073 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1309876 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4497. Min Act: -0.0000

Data Index: 290067 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4380. Min Act: -0.0000

Data Index: 789504 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.5647. Min Range: -0.5647

Max Act: 0.4201. Min Act: -0.0001

Data Index: 449151 (C4 (Web Text))

Max Activating Token Index: 931