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

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

Neuron 3556 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: 0.6885. Min Range: -0.6885

Max Act: 0.6885. Min Act: -0.0001

Data Index: 271213 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6707. Min Act: -0.0001

Data Index: 277566 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6462. Min Act: -0.0001

Data Index: 1013857 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6581. Min Act: -0.0001

Data Index: 1271164 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6353. Min Act: -0.0001

Data Index: 889577 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6343. Min Act: -0.0001

Data Index: 24471 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6307. Min Act: -0.0001

Data Index: 140530 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6272. Min Act: -0.0001

Data Index: 522305 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6245. Min Act: -0.0001

Data Index: 707537 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6051. Min Act: -0.0001

Data Index: 869792 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5668. Min Act: -0.0001

Data Index: 1206276 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5996. Min Act: -0.0001

Data Index: 80918 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5959. Min Act: -0.0001

Data Index: 151068 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5943. Min Act: -0.0001

Data Index: 837459 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5937. Min Act: -0.0001

Data Index: 601253 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1107426 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5891. Min Act: -0.0001

Data Index: 1037084 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5830. Min Act: -0.0001

Data Index: 723091 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1286971 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5961. Min Act: -0.0001

Data Index: 572256 (C4 (Web Text))

Max Activating Token Index: 150