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

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

Neuron 3654 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0003

Data Index: 722082 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0439. Min Act: -0.0002

Data Index: 302205 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0442. Min Act: -0.0002

Data Index: 488434 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0442. Min Act: -0.0003

Data Index: 777325 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0423. Min Act: -0.0002

Data Index: 374933 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1342854 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1025634 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0414. Min Act: -0.0002

Data Index: 22164 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1031493 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0395. Min Act: -0.0002

Data Index: 987501 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0397. Min Act: -0.0003

Data Index: 290045 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0396. Min Act: -0.0002

Data Index: 448892 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0392. Min Act: -0.0002

Data Index: 908561 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0388. Min Act: -0.0003

Data Index: 965094 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0386. Min Act: -0.0002

Data Index: 932168 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0397. Min Act: -0.0003

Data Index: 774877 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0351. Min Act: -0.0002

Data Index: 756077 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1068674 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0363. Min Act: -0.0002

Data Index: 883211 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1496568 (Python Code)

Max Activating Token Index: 503