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

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

Neuron 2375 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.1358. Min Act: -0.0001

Data Index: 1505528 (Python Code)

Max Activating Token Index: 863

Text #1

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.1089. Min Act: -0.0001

Data Index: 1206908 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.1600. Min Act: -0.0001

Data Index: 1438190 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.1938. Min Act: -0.0001

Data Index: 1453504 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.0722. Min Act: -0.0001

Data Index: 1622127 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.0092. Min Act: -0.0001

Data Index: 1472693 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.1034. Min Act: -0.0001

Data Index: 1357625 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.1938. Min Range: -1.1938

Max Act: 0.9730. Min Act: -0.0001

Data Index: 1631363 (Python Code)

Max Activating Token Index: 677

Text #8

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.0296. Min Act: -0.0001

Data Index: 1469766 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 1.1938. Min Range: -1.1938

Max Act: 0.9997. Min Act: -0.0001

Data Index: 1454559 (Python Code)

Max Activating Token Index: 814

Text #10

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.0458. Min Act: -0.0001

Data Index: 1600615 (Python Code)

Max Activating Token Index: 824

Text #11

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.0150. Min Act: -0.0001

Data Index: 987818 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.1938. Min Range: -1.1938

Max Act: 0.9699. Min Act: -0.0001

Data Index: 1396320 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 1.1938. Min Range: -1.1938

Max Act: 0.9760. Min Act: -0.0001

Data Index: 1464221 (Python Code)

Max Activating Token Index: 925

Text #14

Max Range: 1.1938. Min Range: -1.1938

Max Act: 0.8772. Min Act: -0.0001

Data Index: 1554404 (Python Code)

Max Activating Token Index: 891

Text #15

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.0246. Min Act: -0.0001

Data Index: 136343 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.1938. Min Range: -1.1938

Max Act: 0.9022. Min Act: -0.0001

Data Index: 1578720 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 1.1938. Min Range: -1.1938

Max Act: 0.9849. Min Act: -0.0001

Data Index: 1594084 (Python Code)

Max Activating Token Index: 759

Text #18

Max Range: 1.1938. Min Range: -1.1938

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1563776 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 1.1938. Min Range: -1.1938

Max Act: 0.8716. Min Act: -0.0001

Data Index: 1552718 (Python Code)

Max Activating Token Index: 763