Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 588 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0823. Min Act: -0.0002

Data Index: 303806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0739. Min Act: -0.0003

Data Index: 1302163 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0654. Min Act: -0.0002

Data Index: 435357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0636. Min Act: -0.0002

Data Index: 462973 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1235567 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0555. Min Act: -0.0002

Data Index: 179683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0608. Min Act: -0.0002

Data Index: 989192 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0525. Min Act: -0.0002

Data Index: 209999 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0480. Min Act: -0.0002

Data Index: 214452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1306328 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0515. Min Act: -0.0002

Data Index: 352381 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1207804 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0476. Min Act: -0.0002

Data Index: 716425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0500. Min Act: -0.0002

Data Index: 576950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0460. Min Act: -0.0003

Data Index: 981300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0451. Min Act: -0.0003

Data Index: 443126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0485. Min Act: -0.0003

Data Index: 370003 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0387. Min Act: -0.0003

Data Index: 667335 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0346. Min Act: -0.0003

Data Index: 112227 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0350. Min Act: -0.0003

Data Index: 1299848 (C4 (Web Text))

Max Activating Token Index: 1023