Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 521 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0003

Data Index: 690329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0469. Min Act: -0.0003

Data Index: 77999 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1167256 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0517. Min Act: -0.0003

Data Index: 332284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1234440 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1135837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1398583 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1181511 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0455. Min Act: -0.0003

Data Index: 949423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0003

Data Index: 456087 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0463. Min Act: -0.0003

Data Index: 449434 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0428. Min Act: -0.0003

Data Index: 655016 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0449. Min Act: -0.0003

Data Index: 330013 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0433. Min Act: -0.0003

Data Index: 900014 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1059759 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1377153 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1225533 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0438. Min Act: -0.0003

Data Index: 397462 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1001519 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0440. Min Act: -0.0003

Data Index: 494890 (C4 (Web Text))

Max Activating Token Index: 1023