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

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

Neuron 5963 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1529650 (Python Code)

Max Activating Token Index: 251

Text #1

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1573592 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1426504 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1490853 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1632596 (Python Code)

Max Activating Token Index: 922

Text #5

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1408134 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1606849 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1552442 (Python Code)

Max Activating Token Index: 901

Text #8

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1588901 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1540031 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1415079 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1517517 (Python Code)

Max Activating Token Index: 981

Text #12

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1590300 (Python Code)

Max Activating Token Index: 593

Text #13

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1618620 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.6592. Min Act: 0.0000

Data Index: 1463769 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1444523 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1398213 (Python Code)

Max Activating Token Index: 86

Text #17

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1584191 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1555143 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 0.9161. Min Range: -0.9161

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1379512 (Python Code)

Max Activating Token Index: 746