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

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

Neuron 5438 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6586. Min Act: -0.0000

Data Index: 146591 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1448467 (Python Code)

Max Activating Token Index: 177

Text #2

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6148. Min Act: -0.0000

Data Index: 444086 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1244472 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.6008. Min Act: -0.0000

Data Index: 923156 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1596885 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5476. Min Act: -0.0000

Data Index: 243694 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1573184 (Python Code)

Max Activating Token Index: 909

Text #8

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1222445 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5293. Min Act: -0.0000

Data Index: 753913 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5354. Min Act: -0.0000

Data Index: 507385 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5272. Min Act: -0.0000

Data Index: 302048 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5027. Min Act: -0.0000

Data Index: 489973 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5545. Min Act: -0.0000

Data Index: 298096 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5114. Min Act: -0.0000

Data Index: 59436 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5356. Min Act: -0.0000

Data Index: 456991 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5103. Min Act: -0.0000

Data Index: 182422 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.4938. Min Act: -0.0000

Data Index: 868158 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1586055 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 0.6586. Min Range: -0.6586

Max Act: 0.5021. Min Act: -0.0000

Data Index: 888069 (C4 (Web Text))

Max Activating Token Index: 690