Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2056 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.2674. Min Act: -0.0000

Data Index: 412483 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.1179. Min Act: -0.0000

Data Index: 665769 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.0604. Min Act: -0.0000

Data Index: 136306 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.0162. Min Act: -0.0000

Data Index: 575880 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9293. Min Act: -0.0000

Data Index: 827197 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1210354 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9948. Min Act: -0.0000

Data Index: 301085 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9509. Min Act: -0.0000

Data Index: 656085 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1169225 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1086954 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8919. Min Act: -0.0000

Data Index: 419177 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8939. Min Act: -0.0000

Data Index: 438017 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9635. Min Act: -0.0000

Data Index: 439424 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8043. Min Act: -0.0000

Data Index: 462381 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8576. Min Act: -0.0000

Data Index: 720067 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1323171 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8583. Min Act: -0.0000

Data Index: 437531 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8567. Min Act: -0.0000

Data Index: 882240 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9539. Min Act: -0.0000

Data Index: 245793 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1148632 (C4 (Web Text))

Max Activating Token Index: 830