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

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

Neuron 2195 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: 1.0943. Min Range: -1.0943

Max Act: 1.0943. Min Act: -0.0000

Data Index: 999186 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.9408. Min Act: -0.0000

Data Index: 404724 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7560. Min Act: -0.0000

Data Index: 230968 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7322. Min Act: -0.0000

Data Index: 241449 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7404. Min Act: -0.0000

Data Index: 54883 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6857. Min Act: -0.0000

Data Index: 550656 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7347. Min Act: -0.0000

Data Index: 834405 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1117475 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7178. Min Act: -0.0000

Data Index: 272956 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6789. Min Act: -0.0000

Data Index: 726174 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7756. Min Act: -0.0000

Data Index: 206775 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6939. Min Act: -0.0000

Data Index: 363768 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6864. Min Act: 0.0000

Data Index: 1228241 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6800. Min Act: -0.0000

Data Index: 499018 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6574. Min Act: -0.0000

Data Index: 319298 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7534. Min Act: -0.0000

Data Index: 819545 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6466. Min Act: -0.0000

Data Index: 325646 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6914. Min Act: -0.0000

Data Index: 113011 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6796. Min Act: -0.0000

Data Index: 792830 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7000. Min Act: -0.0000

Data Index: 848704 (C4 (Web Text))

Max Activating Token Index: 813