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

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

Neuron 604 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.9719. Min Act: -0.0002

Data Index: 908183 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5261. Min Act: -0.0002

Data Index: 989380 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.6561. Min Act: -0.0002

Data Index: 262780 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.8955. Min Act: -0.0002

Data Index: 369917 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.6368. Min Act: -0.0002

Data Index: 535016 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.7888. Min Act: -0.0002

Data Index: 1353856 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5132. Min Act: -0.0002

Data Index: 1473192 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5584. Min Act: -0.0002

Data Index: 1306214 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.6448. Min Act: -0.0002

Data Index: 698914 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4069. Min Act: -0.0002

Data Index: 794582 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5181. Min Act: -0.0002

Data Index: 1400913 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.6294. Min Act: -0.0002

Data Index: 949505 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4595. Min Act: -0.0002

Data Index: 1246200 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4804. Min Act: -0.0002

Data Index: 599782 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4011. Min Act: -0.0002

Data Index: 1257274 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4464. Min Act: -0.0002

Data Index: 716433 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.4685. Min Act: -0.0002

Data Index: 1410706 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.5865. Min Act: -0.0002

Data Index: 521495 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3407. Min Act: -0.0002

Data Index: 1407067 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 1.9719. Min Range: -1.9719

Max Act: 1.3828. Min Act: -0.0002

Data Index: 1651603 (Python Code)

Max Activating Token Index: 965