Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 723 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0002

Data Index: 622030 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0476. Min Act: -0.0001

Data Index: 20039 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1162454 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0441. Min Act: -0.0002

Data Index: 959390 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1025582 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1481423 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0444. Min Act: -0.0002

Data Index: 977092 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0435. Min Act: -0.0002

Data Index: 226219 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0439. Min Act: -0.0002

Data Index: 402033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1180416 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1467730 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1583583 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1653153 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0427. Min Act: -0.0002

Data Index: 838575 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1624550 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1633142 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1331396 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1132205 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0404. Min Act: -0.0003

Data Index: 295117 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1166486 (C4 (Web Text))

Max Activating Token Index: 1023