Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2474 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1978519 (The Pile)

Max Activating Token Index: 809

Text #1

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1034217 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.1055. Min Act: -0.0000

Data Index: 28089 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1002783 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9901. Min Act: -0.0000

Data Index: 791379 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1881816 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1655396 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1210412 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1292656 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1640033 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.8540. Min Act: -0.0000

Data Index: 422770 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.8463. Min Act: -0.0000

Data Index: 429831 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1827806 (The Pile)

Max Activating Token Index: 68

Text #13

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1464792 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9024. Min Act: -0.0000

Data Index: 197470 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.7922. Min Act: -0.0000

Data Index: 61246 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.7585. Min Act: -0.0000

Data Index: 736369 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.8353. Min Act: -0.0000

Data Index: 654018 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1521382 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1242186 (The Pile)

Max Activating Token Index: 394