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

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

Neuron 2246 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1993. Min Range: -1.1993

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1139200 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.1993. Min Range: -1.1993

Max Act: 1.0663. Min Act: -0.0000

Data Index: 45946 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.9547. Min Act: -0.0000

Data Index: 39379 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.1993. Min Range: -1.1993

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1105928 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.9690. Min Act: -0.0000

Data Index: 304944 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.9026. Min Act: -0.0000

Data Index: 850188 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.9178. Min Act: -0.0000

Data Index: 928424 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.9122. Min Act: -0.0000

Data Index: 584983 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8816. Min Act: -0.0000

Data Index: 496180 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8332. Min Act: -0.0000

Data Index: 141418 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1308895 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8703. Min Act: -0.0000

Data Index: 82455 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8287. Min Act: -0.0000

Data Index: 578928 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1271808 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1085286 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.7550. Min Act: -0.0000

Data Index: 212405 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.7765. Min Act: -0.0000

Data Index: 106361 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8201. Min Act: -0.0000

Data Index: 628949 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8008. Min Act: -0.0000

Data Index: 589634 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8198. Min Act: -0.0000

Data Index: 703503 (C4 (Web Text))

Max Activating Token Index: 528