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

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

Neuron 5024 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7853. Min Range: -7.7853

Max Act: 7.7853. Min Act: -0.0000

Data Index: 728912 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 7.7853. Min Range: -7.7853

Max Act: 7.4152. Min Act: -0.0000

Data Index: 615967 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 7.7853. Min Range: -7.7853

Max Act: 6.8405. Min Act: -0.0000

Data Index: 1321757 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 7.7853. Min Range: -7.7853

Max Act: 6.8181. Min Act: -0.0000

Data Index: 432424 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 7.7853. Min Range: -7.7853

Max Act: 6.5090. Min Act: -0.0000

Data Index: 164590 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 7.7853. Min Range: -7.7853

Max Act: 6.0368. Min Act: -0.0000

Data Index: 1016475 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.9977. Min Act: -0.0000

Data Index: 565072 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.9868. Min Act: -0.0000

Data Index: 813892 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.9704. Min Act: -0.0000

Data Index: 194429 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.5503. Min Act: -0.0000

Data Index: 819427 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.3341. Min Act: -0.0000

Data Index: 962944 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.2856. Min Act: -0.0000

Data Index: 103919 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.4029. Min Act: -0.0000

Data Index: 1029461 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.4103. Min Act: -0.0000

Data Index: 304698 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.1311. Min Act: -0.0000

Data Index: 451251 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.3202. Min Act: -0.0000

Data Index: 313717 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.2530. Min Act: -0.0000

Data Index: 766753 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.2089. Min Act: -0.0000

Data Index: 288449 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 7.7853. Min Range: -7.7853

Max Act: 5.3769. Min Act: -0.0000

Data Index: 435682 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 7.7853. Min Range: -7.7853

Max Act: 4.9346. Min Act: -0.0000

Data Index: 1325402 (C4 (Web Text))

Max Activating Token Index: 65