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

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

Neuron 2048 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: 1.6965. Min Range: -1.6965

Max Act: 1.6965. Min Act: -0.0000

Data Index: 641615 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.2931. Min Act: -0.0000

Data Index: 509984 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 1.6965. Min Range: -1.6965

Max Act: 1.0700. Min Act: -0.0000

Data Index: 457272 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1197054 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.9747. Min Act: -0.0000

Data Index: 629812 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1292566 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.8934. Min Act: 0.0000

Data Index: 526723 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.8746. Min Act: -0.0000

Data Index: 538164 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.8341. Min Act: -0.0000

Data Index: 131461 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.8063. Min Act: -0.0000

Data Index: 730951 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.8319. Min Act: -0.0000

Data Index: 136750 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.6802. Min Act: -0.0000

Data Index: 927558 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.7068. Min Act: -0.0000

Data Index: 342605 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1139556 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.7744. Min Act: 0.0000

Data Index: 8690 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.7482. Min Act: -0.0000

Data Index: 867280 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1003752 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1130683 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1096711 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.6965. Min Range: -1.6965

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1357053 (C4 (Web Text))

Max Activating Token Index: 384