Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2459 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0742. Min Range: -4.0742

Max Act: 4.0742. Min Act: -0.0000

Data Index: 18094 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 4.0742. Min Range: -4.0742

Max Act: 3.6871. Min Act: -0.0000

Data Index: 211293 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 4.0742. Min Range: -4.0742

Max Act: 3.3442. Min Act: -0.0000

Data Index: 103920 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 4.0742. Min Range: -4.0742

Max Act: 3.3429. Min Act: -0.0000

Data Index: 1252911 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 4.0742. Min Range: -4.0742

Max Act: 3.4062. Min Act: -0.0000

Data Index: 473799 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 4.0742. Min Range: -4.0742

Max Act: 3.2366. Min Act: -0.0000

Data Index: 736292 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 4.0742. Min Range: -4.0742

Max Act: 3.1576. Min Act: -0.0000

Data Index: 930908 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 4.0742. Min Range: -4.0742

Max Act: 3.1435. Min Act: -0.0000

Data Index: 467252 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 4.0742. Min Range: -4.0742

Max Act: 3.3220. Min Act: -0.0000

Data Index: 957825 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.9461. Min Act: -0.0000

Data Index: 760273 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.8863. Min Act: -0.0000

Data Index: 1033320 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.7616. Min Act: -0.0000

Data Index: 1318075 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.8548. Min Act: -0.0000

Data Index: 181479 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.8589. Min Act: -0.0000

Data Index: 538225 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.7461. Min Act: -0.0000

Data Index: 946523 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.7082. Min Act: -0.0000

Data Index: 1216334 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.6393. Min Act: -0.0000

Data Index: 838988 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.5016. Min Act: -0.0000

Data Index: 300466 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.5632. Min Act: -0.0000

Data Index: 134401 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 4.0742. Min Range: -4.0742

Max Act: 2.4934. Min Act: -0.0000

Data Index: 850509 (C4 (Web Text))

Max Activating Token Index: 893