Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.4277. Min Act: -0.0001

Data Index: 114378 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3849. Min Act: -0.0000

Data Index: 144748 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3714. Min Act: -0.0001

Data Index: 1556347 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3538. Min Act: -0.0001

Data Index: 1508187 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3467. Min Act: -0.0001

Data Index: 492022 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3031. Min Act: -0.0001

Data Index: 1543173 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2790. Min Act: -0.0001

Data Index: 1171511 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3009. Min Act: -0.0001

Data Index: 1372310 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2952. Min Act: -0.0001

Data Index: 406415 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1400669 (Python Code)

Max Activating Token Index: 485

Text #10

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2824. Min Act: -0.0000

Data Index: 921499 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3181. Min Act: -0.0001

Data Index: 1569727 (Python Code)

Max Activating Token Index: 717

Text #12

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2856. Min Act: -0.0001

Data Index: 481423 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2945. Min Act: -0.0001

Data Index: 1530476 (Python Code)

Max Activating Token Index: 421

Text #14

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1481577 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2866. Min Act: -0.0001

Data Index: 1086323 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2913. Min Act: -0.0000

Data Index: 838855 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2868. Min Act: -0.0001

Data Index: 1425128 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2866. Min Act: -0.0000

Data Index: 768384 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3137. Min Act: -0.0001

Data Index: 710962 (C4 (Web Text))

Max Activating Token Index: 367