Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 523 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.5091. Min Act: -0.0001

Data Index: 1547222 (Python Code)

Max Activating Token Index: 194

Text #1

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4725. Min Act: -0.0001

Data Index: 1463762 (Python Code)

Max Activating Token Index: 363

Text #2

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4414. Min Act: -0.0001

Data Index: 1546040 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1568589 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4428. Min Act: -0.0001

Data Index: 1520572 (Python Code)

Max Activating Token Index: 997

Text #5

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4432. Min Act: -0.0001

Data Index: 1596192 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4501. Min Act: 0.0000

Data Index: 1522566 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4271. Min Act: -0.0001

Data Index: 1409567 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4357. Min Act: -0.0001

Data Index: 1428418 (Python Code)

Max Activating Token Index: 799

Text #9

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1448629 (Python Code)

Max Activating Token Index: 179

Text #10

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4262. Min Act: -0.0001

Data Index: 1384843 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4333. Min Act: -0.0001

Data Index: 1508611 (Python Code)

Max Activating Token Index: 205

Text #12

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3997. Min Act: -0.0001

Data Index: 1526196 (Python Code)

Max Activating Token Index: 926

Text #13

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4145. Min Act: -0.0001

Data Index: 1380980 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4549. Min Act: -0.0001

Data Index: 1444198 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3935. Min Act: -0.0001

Data Index: 94935 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4575. Min Act: -0.0001

Data Index: 1579653 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3852. Min Act: -0.0001

Data Index: 1441771 (Python Code)

Max Activating Token Index: 595

Text #18

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1481054 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3679. Min Act: -0.0001

Data Index: 1484807 (Python Code)

Max Activating Token Index: 240