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

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

Neuron 1303 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.9817. Min Act: -0.0000

Data Index: 168672 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.0417. Min Range: -1.0417

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1593207 (Python Code)

Max Activating Token Index: 253

Text #2

Max Range: 1.0417. Min Range: -1.0417

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1385285 (Python Code)

Max Activating Token Index: 523

Text #3

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1519949 (Python Code)

Max Activating Token Index: 542

Text #4

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.9045. Min Act: -0.0000

Data Index: 384220 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.9004. Min Act: -0.0001

Data Index: 998817 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1541317 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1369069 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1575254 (Python Code)

Max Activating Token Index: 717

Text #9

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1567200 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8340. Min Act: -0.0001

Data Index: 244574 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1587107 (Python Code)

Max Activating Token Index: 664

Text #12

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1526678 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1573114 (Python Code)

Max Activating Token Index: 122

Text #14

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1419271 (Python Code)

Max Activating Token Index: 795

Text #15

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1387327 (Python Code)

Max Activating Token Index: 693

Text #16

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1607519 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1492315 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1435171 (Python Code)

Max Activating Token Index: 350

Text #19

Max Range: 1.0417. Min Range: -1.0417

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1546772 (Python Code)

Max Activating Token Index: 553