Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2979 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.9426. Min Act: -0.0001

Data Index: 645253 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8708. Min Act: -0.0001

Data Index: 911001 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8205. Min Act: -0.0001

Data Index: 338928 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8385. Min Act: -0.0000

Data Index: 122279 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7934. Min Act: -0.0001

Data Index: 77648 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1120787 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1184005 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8053. Min Act: -0.0001

Data Index: 866767 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8032. Min Act: -0.0001

Data Index: 38808 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7480. Min Act: -0.0001

Data Index: 215553 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7866. Min Act: -0.0001

Data Index: 460385 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8049. Min Act: -0.0001

Data Index: 21002 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7504. Min Act: -0.0001

Data Index: 351762 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7930. Min Act: -0.0001

Data Index: 427324 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7440. Min Act: -0.0000

Data Index: 327 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7612. Min Act: -0.0001

Data Index: 1194975 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8249. Min Act: -0.0001

Data Index: 337985 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7697. Min Act: -0.0000

Data Index: 311801 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7312. Min Act: -0.0001

Data Index: 899150 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7302. Min Act: -0.0001

Data Index: 560145 (C4 (Web Text))

Max Activating Token Index: 639