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

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

Neuron 3353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6404. Min Act: -0.0001

Data Index: 500000 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6662. Min Act: -0.0001

Data Index: 943969 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6133. Min Act: -0.0001

Data Index: 617322 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5702. Min Act: -0.0001

Data Index: 497065 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5208. Min Act: -0.0001

Data Index: 683411 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5677. Min Act: -0.0001

Data Index: 494541 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5067. Min Act: -0.0001

Data Index: 545264 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5533. Min Act: -0.0001

Data Index: 48426 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5518. Min Act: -0.0001

Data Index: 339290 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5297. Min Act: -0.0001

Data Index: 1089334 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5293. Min Act: -0.0001

Data Index: 1276856 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5650. Min Act: -0.0001

Data Index: 308862 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5461. Min Act: -0.0001

Data Index: 717455 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5225. Min Act: -0.0001

Data Index: 1352661 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5321. Min Act: -0.0001

Data Index: 1280717 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5051. Min Act: -0.0001

Data Index: 632786 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5530. Min Act: -0.0001

Data Index: 791587 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4795. Min Act: -0.0001

Data Index: 672045 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.5081. Min Act: -0.0001

Data Index: 945826 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.4905. Min Act: -0.0001

Data Index: 379394 (C4 (Web Text))

Max Activating Token Index: 737