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

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

Neuron 3192 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.8764. Min Act: -0.0003

Data Index: 1403859 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.6066. Min Act: -0.0003

Data Index: 1406402 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.7845. Min Act: -0.0003

Data Index: 1589706 (Python Code)

Max Activating Token Index: 653

Text #3

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5433. Min Act: -0.0003

Data Index: 1402318 (Python Code)

Max Activating Token Index: 881

Text #4

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5758. Min Act: -0.0003

Data Index: 1469524 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5977. Min Act: -0.0003

Data Index: 1484541 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.6301. Min Act: -0.0003

Data Index: 1418919 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4661. Min Act: -0.0003

Data Index: 1640118 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4583. Min Act: -0.0003

Data Index: 1565109 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4303. Min Act: -0.0004

Data Index: 1586613 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4652. Min Act: -0.0003

Data Index: 1400244 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4194. Min Act: -0.0003

Data Index: 1600300 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.3385. Min Act: -0.0003

Data Index: 1455385 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5882. Min Act: -0.0004

Data Index: 1574338 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5845. Min Act: -0.0003

Data Index: 1359876 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4953. Min Act: -0.0003

Data Index: 1576794 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.4541. Min Act: -0.0003

Data Index: 1626762 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5191. Min Act: -0.0004

Data Index: 1580308 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5103. Min Act: -0.0003

Data Index: 1593790 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 1.8764. Min Range: -1.8764

Max Act: 1.5069. Min Act: -0.0003

Data Index: 1425733 (Python Code)

Max Activating Token Index: 204