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

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

Neuron 1356 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1024797 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6931. Min Act: -0.0000

Data Index: 137025 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1342806 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6527. Min Act: -0.0000

Data Index: 540977 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6767. Min Act: -0.0000

Data Index: 382900 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1191034 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1265723 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5726. Min Act: -0.0000

Data Index: 946529 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6035. Min Act: -0.0000

Data Index: 896468 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1303895 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6506. Min Act: -0.0000

Data Index: 192072 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6075. Min Act: -0.0001

Data Index: 414744 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5488. Min Act: -0.0000

Data Index: 913149 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6158. Min Act: -0.0000

Data Index: 618774 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6117. Min Act: -0.0000

Data Index: 387836 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5396. Min Act: -0.0001

Data Index: 537803 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5668. Min Act: -0.0000

Data Index: 928871 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5466. Min Act: -0.0000

Data Index: 325648 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5847. Min Act: -0.0000

Data Index: 840282 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5638. Min Act: -0.0000

Data Index: 880497 (C4 (Web Text))

Max Activating Token Index: 802