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

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

Neuron 3835 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: 0.6957. Min Range: -0.6957

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1257950 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5866. Min Act: -0.0001

Data Index: 315901 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5774. Min Act: -0.0001

Data Index: 1113874 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5983. Min Act: -0.0000

Data Index: 825851 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5681. Min Act: -0.0001

Data Index: 513311 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5666. Min Act: -0.0001

Data Index: 44209 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5735. Min Act: -0.0001

Data Index: 484520 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5703. Min Act: -0.0001

Data Index: 647077 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5661. Min Act: -0.0001

Data Index: 1157094 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5713. Min Act: -0.0001

Data Index: 46390 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5821. Min Act: -0.0001

Data Index: 1250164 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5460. Min Act: -0.0001

Data Index: 585720 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5642. Min Act: -0.0001

Data Index: 613771 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5640. Min Act: -0.0001

Data Index: 1211425 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5157. Min Act: -0.0001

Data Index: 618567 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5333. Min Act: -0.0000

Data Index: 544676 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5588. Min Act: -0.0001

Data Index: 772747 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5523. Min Act: -0.0000

Data Index: 169102 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5352. Min Act: -0.0001

Data Index: 353511 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5614. Min Act: -0.0001

Data Index: 1268769 (C4 (Web Text))

Max Activating Token Index: 215