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

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

Neuron 635 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: 0.6825. Min Range: -0.6825

Max Act: 0.6825. Min Act: -0.0000

Data Index: 112722 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6814. Min Act: -0.0000

Data Index: 810228 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6249. Min Act: -0.0000

Data Index: 113980 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6415. Min Act: -0.0000

Data Index: 48423 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6322. Min Act: -0.0000

Data Index: 379089 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6289. Min Act: -0.0000

Data Index: 659697 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6332. Min Act: -0.0000

Data Index: 184921 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5850. Min Act: -0.0000

Data Index: 592983 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1211399 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5571. Min Act: -0.0000

Data Index: 817708 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5327. Min Act: -0.0000

Data Index: 101056 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5514. Min Act: -0.0000

Data Index: 319294 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5459. Min Act: -0.0000

Data Index: 568753 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5622. Min Act: -0.0000

Data Index: 129459 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5553. Min Act: -0.0000

Data Index: 560540 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5059. Min Act: -0.0000

Data Index: 401181 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5319. Min Act: -0.0000

Data Index: 376389 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5323. Min Act: -0.0000

Data Index: 843194 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5493. Min Act: -0.0000

Data Index: 540143 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1143880 (C4 (Web Text))

Max Activating Token Index: 688