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

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

Neuron 5091 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.5003. Min Act: -0.0000

Data Index: 965943 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4928. Min Act: -0.0000

Data Index: 614846 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4778. Min Act: -0.0000

Data Index: 371035 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4195. Min Act: -0.0000

Data Index: 997502 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3803. Min Act: -0.0000

Data Index: 921005 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3564. Min Act: -0.0000

Data Index: 223810 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1308464 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1078044 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3595. Min Act: -0.0000

Data Index: 612221 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3319. Min Act: -0.0000

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3307. Min Act: -0.0000

Data Index: 770663 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3405. Min Act: -0.0000

Data Index: 255820 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3204. Min Act: -0.0000

Data Index: 636084 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3216. Min Act: -0.0000

Data Index: 505463 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3228. Min Act: 0.0000

Data Index: 373546 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1161875 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3206. Min Act: -0.0000

Data Index: 982317 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3069. Min Act: -0.0000

Data Index: 35884 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3076. Min Act: -0.0000

Data Index: 672156 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3045. Min Act: -0.0000

Data Index: 983319 (C4 (Web Text))

Max Activating Token Index: 142