Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3691 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0002

Data Index: 900141 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0475. Min Act: -0.0002

Data Index: 9943 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0445. Min Act: -0.0002

Data Index: 408175 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0443. Min Act: -0.0002

Data Index: 292833 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0475. Min Act: -0.0002

Data Index: 183302 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0478. Min Act: -0.0002

Data Index: 883887 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1070643 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0450. Min Act: -0.0002

Data Index: 785956 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0479. Min Act: -0.0002

Data Index: 81927 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1009712 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0434. Min Act: -0.0002

Data Index: 229229 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0410. Min Act: -0.0002

Data Index: 97401 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0422. Min Act: -0.0002

Data Index: 337749 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0380. Min Act: -0.0002

Data Index: 469896 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1299156 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0392. Min Act: -0.0002

Data Index: 547627 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0395. Min Act: -0.0002

Data Index: 570715 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0445. Min Act: -0.0002

Data Index: 685475 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0409. Min Act: -0.0002

Data Index: 297426 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1347510 (C4 (Web Text))

Max Activating Token Index: 172