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

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

Neuron 3840 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4294. Min Range: -2.4294

Max Act: 2.4294. Min Act: -0.0000

Data Index: 619144 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 2.4294. Min Range: -2.4294

Max Act: 2.2204. Min Act: -0.0000

Data Index: 578749 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.9522. Min Act: -0.0000

Data Index: 355976 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.9224. Min Act: -0.0000

Data Index: 150539 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 2.4294. Min Range: -2.4294

Max Act: 2.1290. Min Act: -0.0000

Data Index: 859394 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1342946 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.8088. Min Act: -0.0000

Data Index: 1266360 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.9549. Min Act: -0.0000

Data Index: 931283 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.9497. Min Act: -0.0000

Data Index: 1237727 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.6397. Min Act: -0.0000

Data Index: 420007 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.8453. Min Act: -0.0000

Data Index: 35267 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.7077. Min Act: -0.0000

Data Index: 117263 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.5765. Min Act: -0.0000

Data Index: 8707 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.8008. Min Act: -0.0000

Data Index: 468453 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.7733. Min Act: -0.0000

Data Index: 385833 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.7776. Min Act: -0.0000

Data Index: 495098 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.7754. Min Act: -0.0000

Data Index: 521499 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.5700. Min Act: -0.0000

Data Index: 981700 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.7686. Min Act: -0.0000

Data Index: 31211 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 2.4294. Min Range: -2.4294

Max Act: 1.6514. Min Act: -0.0000

Data Index: 812301 (C4 (Web Text))

Max Activating Token Index: 640