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

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

Neuron 84 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7832. Min Act: -0.0000

Data Index: 394579 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1125083 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7956. Min Act: -0.0000

Data Index: 133900 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6268. Min Act: -0.0000

Data Index: 316863 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6284. Min Act: -0.0000

Data Index: 613008 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6360. Min Act: -0.0000

Data Index: 993987 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6033. Min Act: -0.0000

Data Index: 774682 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1003490 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6144. Min Act: -0.0000

Data Index: 654414 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5958. Min Act: -0.0000

Data Index: 471879 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1343843 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5714. Min Act: -0.0000

Data Index: 414301 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5430. Min Act: -0.0000

Data Index: 342042 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1046569 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1058688 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.4953. Min Act: -0.0000

Data Index: 482775 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5506. Min Act: -0.0000

Data Index: 988951 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1042699 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5496. Min Act: -0.0000

Data Index: 183147 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.5434. Min Act: -0.0000

Data Index: 219875 (C4 (Web Text))

Max Activating Token Index: 946