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

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

Neuron 2825 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.3091. Min Act: -0.0003

Data Index: 57760 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2659. Min Act: -0.0003

Data Index: 1519857 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.1011. Min Act: -0.0003

Data Index: 1595696 (Python Code)

Max Activating Token Index: 986

Text #3

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1524939 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1458089 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1531712 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1459395 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0521. Min Act: -0.0003

Data Index: 551631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1549321 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0502. Min Act: -0.0003

Data Index: 958559 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1486037 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1371636 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1636812 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1547847 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1479019 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1427671 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1412363 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1626299 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1567254 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1066650 (C4 (Web Text))

Max Activating Token Index: 1023