Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1502 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0006

Data Index: 258156 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0464. Min Act: -0.0006

Data Index: 397942 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0493. Min Act: -0.0006

Data Index: 1093026 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0446. Min Act: -0.0006

Data Index: 112215 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0440. Min Act: -0.0006

Data Index: 734018 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0445. Min Act: -0.0006

Data Index: 942694 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0424. Min Act: -0.0006

Data Index: 114868 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0448. Min Act: -0.0006

Data Index: 739337 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0429. Min Act: -0.0006

Data Index: 694469 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0431. Min Act: -0.0006

Data Index: 356637 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0428. Min Act: -0.0006

Data Index: 260756 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0431. Min Act: -0.0006

Data Index: 595800 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0422. Min Act: -0.0006

Data Index: 92153 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0430. Min Act: -0.0006

Data Index: 691967 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0413. Min Act: -0.0006

Data Index: 551329 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0421. Min Act: -0.0006

Data Index: 71193 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0410. Min Act: -0.0006

Data Index: 550870 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0419. Min Act: -0.0006

Data Index: 453577 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0410. Min Act: -0.0006

Data Index: 19244 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0428. Min Act: -0.0006

Data Index: 1307748 (C4 (Web Text))

Max Activating Token Index: 875