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

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

Neuron 2481 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: 5.1917. Min Range: -5.1917

Max Act: 4.6092. Min Act: -0.0000

Data Index: 1515966 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.7850. Min Act: -0.0000

Data Index: 1439471 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 5.1917. Min Range: -5.1917

Max Act: 5.1747. Min Act: -0.0000

Data Index: 1459119 (Python Code)

Max Activating Token Index: 611

Text #3

Max Range: 5.1917. Min Range: -5.1917

Max Act: 5.1917. Min Act: -0.0000

Data Index: 1449753 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.4293. Min Act: -0.0000

Data Index: 1486925 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.2453. Min Act: -0.0000

Data Index: 1384965 (Python Code)

Max Activating Token Index: 142

Text #6

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.8170. Min Act: -0.0000

Data Index: 1568306 (Python Code)

Max Activating Token Index: 939

Text #7

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.6347. Min Act: -0.0000

Data Index: 1459419 (Python Code)

Max Activating Token Index: 340

Text #8

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.4297. Min Act: -0.0000

Data Index: 1508377 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.3851. Min Act: -0.0000

Data Index: 1444903 (Python Code)

Max Activating Token Index: 948

Text #10

Max Range: 5.1917. Min Range: -5.1917

Max Act: 3.9827. Min Act: -0.0000

Data Index: 1418347 (Python Code)

Max Activating Token Index: 376

Text #11

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.3460. Min Act: -0.0000

Data Index: 1495952 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.2405. Min Act: -0.0000

Data Index: 1543174 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.2271. Min Act: -0.0000

Data Index: 1602217 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.5878. Min Act: -0.0000

Data Index: 1483093 (Python Code)

Max Activating Token Index: 864

Text #15

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.1716. Min Act: -0.0000

Data Index: 1509736 (Python Code)

Max Activating Token Index: 744

Text #16

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.5095. Min Act: -0.0000

Data Index: 1653325 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.3470. Min Act: -0.0000

Data Index: 1391093 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.3173. Min Act: -0.0000

Data Index: 1602031 (Python Code)

Max Activating Token Index: 516

Text #19

Max Range: 5.1917. Min Range: -5.1917

Max Act: 4.1165. Min Act: -0.0000

Data Index: 1558171 (Python Code)

Max Activating Token Index: 791