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

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

Neuron 5565 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.6012. Min Act: -0.0001

Data Index: 1648385 (Python Code)

Max Activating Token Index: 263

Text #1

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5673. Min Act: -0.0001

Data Index: 1624961 (Python Code)

Max Activating Token Index: 940

Text #2

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1503689 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1525677 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5409. Min Act: -0.0001

Data Index: 1491573 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5409. Min Act: -0.0001

Data Index: 1522740 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5306. Min Act: -0.0001

Data Index: 1541444 (Python Code)

Max Activating Token Index: 88

Text #7

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5209. Min Act: -0.0001

Data Index: 1532364 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5041. Min Act: -0.0001

Data Index: 1538042 (Python Code)

Max Activating Token Index: 953

Text #9

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5061. Min Act: -0.0001

Data Index: 1453845 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5136. Min Act: -0.0001

Data Index: 1387690 (Python Code)

Max Activating Token Index: 542

Text #11

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5000. Min Act: -0.0001

Data Index: 1408623 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5077. Min Act: -0.0001

Data Index: 1375194 (Python Code)

Max Activating Token Index: 1000

Text #13

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1385236 (Python Code)

Max Activating Token Index: 390

Text #14

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5059. Min Act: -0.0001

Data Index: 1596967 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5008. Min Act: -0.0001

Data Index: 1442445 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5027. Min Act: -0.0001

Data Index: 1446088 (Python Code)

Max Activating Token Index: 1015

Text #17

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4892. Min Act: -0.0001

Data Index: 1636881 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4897. Min Act: -0.0001

Data Index: 1469033 (Python Code)

Max Activating Token Index: 618

Text #19

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4932. Min Act: -0.0001

Data Index: 1593571 (Python Code)

Max Activating Token Index: 524