Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.9858. Min Act: -0.0000

Data Index: 890082 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.8823. Min Act: -0.0000

Data Index: 195895 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.8440. Min Act: -0.0000

Data Index: 709122 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 2.0429. Min Range: -2.0429

Max Act: 2.0429. Min Act: -0.0000

Data Index: 1491677 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 2.0429. Min Range: -2.0429

Max Act: 2.0124. Min Act: -0.0000

Data Index: 413807 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.7369. Min Act: -0.0000

Data Index: 315264 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.9352. Min Act: -0.0000

Data Index: 179608 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.7114. Min Act: -0.0000

Data Index: 1173033 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.9019. Min Act: -0.0000

Data Index: 1622520 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.7041. Min Act: -0.0000

Data Index: 1577465 (Python Code)

Max Activating Token Index: 963

Text #10

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.7948. Min Act: -0.0000

Data Index: 1355887 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.6626. Min Act: -0.0000

Data Index: 1626966 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.6503. Min Act: -0.0000

Data Index: 67345 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.7386. Min Act: -0.0000

Data Index: 397909 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.7168. Min Act: -0.0000

Data Index: 963939 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.6083. Min Act: -0.0000

Data Index: 588236 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.7092. Min Act: -0.0000

Data Index: 963462 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.6395. Min Act: -0.0000

Data Index: 1287631 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.6323. Min Act: -0.0000

Data Index: 380163 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 2.0429. Min Range: -2.0429

Max Act: 1.6286. Min Act: -0.0000

Data Index: 1080259 (C4 (Web Text))

Max Activating Token Index: 845