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

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

Neuron 765 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8763. Min Act: -0.0000

Data Index: 941946 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8338. Min Act: -0.0000

Data Index: 204109 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1020858 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1510605 (Python Code)

Max Activating Token Index: 447

Text #4

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7094. Min Act: -0.0000

Data Index: 683197 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1387941 (Python Code)

Max Activating Token Index: 474

Text #6

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1245748 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7377. Min Act: -0.0000

Data Index: 244937 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1196208 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6882. Min Act: -0.0000

Data Index: 280502 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1502768 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1509687 (Python Code)

Max Activating Token Index: 997

Text #12

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6686. Min Act: -0.0000

Data Index: 281515 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1214400 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6678. Min Act: -0.0000

Data Index: 876361 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6201. Min Act: -0.0000

Data Index: 353029 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.5986. Min Act: -0.0000

Data Index: 970114 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1331597 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1031879 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.5178. Min Act: -0.0000

Data Index: 417471 (C4 (Web Text))

Max Activating Token Index: 866