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

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

Neuron 5545 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: 6.4377. Min Range: -6.4377

Max Act: 6.4377. Min Act: -0.0000

Data Index: 1462692 (Python Code)

Max Activating Token Index: 197

Text #1

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.9653. Min Act: -0.0000

Data Index: 1373903 (Python Code)

Max Activating Token Index: 957

Text #2

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.9470. Min Act: -0.0001

Data Index: 1652721 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 6.4377. Min Range: -6.4377

Max Act: 6.0144. Min Act: -0.0000

Data Index: 1396709 (Python Code)

Max Activating Token Index: 186

Text #4

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.8216. Min Act: -0.0000

Data Index: 1436167 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.9566. Min Act: -0.0000

Data Index: 1535017 (Python Code)

Max Activating Token Index: 260

Text #6

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.7735. Min Act: -0.0000

Data Index: 1549827 (Python Code)

Max Activating Token Index: 105

Text #7

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.9420. Min Act: -0.0000

Data Index: 1614936 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.7027. Min Act: -0.0000

Data Index: 1362642 (Python Code)

Max Activating Token Index: 754

Text #9

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.8774. Min Act: -0.0001

Data Index: 1517663 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.8441. Min Act: -0.0000

Data Index: 1370802 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.8213. Min Act: -0.0001

Data Index: 1406810 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.8422. Min Act: -0.0000

Data Index: 1617426 (Python Code)

Max Activating Token Index: 160

Text #13

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.9929. Min Act: -0.0000

Data Index: 1647076 (Python Code)

Max Activating Token Index: 945

Text #14

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.8333. Min Act: -0.0001

Data Index: 1605963 (Python Code)

Max Activating Token Index: 198

Text #15

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.6076. Min Act: -0.0000

Data Index: 1460687 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.9537. Min Act: -0.0000

Data Index: 1569633 (Python Code)

Max Activating Token Index: 223

Text #17

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.9352. Min Act: -0.0000

Data Index: 1430517 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.5920. Min Act: -0.0000

Data Index: 1396774 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 6.4377. Min Range: -6.4377

Max Act: 5.6070. Min Act: -0.0000

Data Index: 1640762 (Python Code)

Max Activating Token Index: 772