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

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

Neuron 3255 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: 1.1955. Min Range: -1.1955

Max Act: 1.1955. Min Act: -0.0001

Data Index: 689538 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9885. Min Act: -0.0001

Data Index: 617187 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9829. Min Act: -0.0001

Data Index: 478975 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9406. Min Act: -0.0001

Data Index: 377898 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8470. Min Act: -0.0001

Data Index: 281196 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8903. Min Act: -0.0001

Data Index: 1111615 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9024. Min Act: -0.0001

Data Index: 773275 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8934. Min Act: -0.0001

Data Index: 879265 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8686. Min Act: -0.0001

Data Index: 758625 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8971. Min Act: -0.0001

Data Index: 74679 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8944. Min Act: -0.0001

Data Index: 1345718 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8832. Min Act: -0.0001

Data Index: 395083 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8644. Min Act: -0.0001

Data Index: 939487 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9382. Min Act: -0.0001

Data Index: 926976 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8483. Min Act: -0.0001

Data Index: 782736 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7945. Min Act: -0.0001

Data Index: 1134098 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1256230 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8064. Min Act: -0.0001

Data Index: 1167671 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7963. Min Act: -0.0001

Data Index: 664353 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7700. Min Act: -0.0001

Data Index: 799709 (C4 (Web Text))

Max Activating Token Index: 119