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

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

Neuron 240 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0825. Min Range: -1.0825

Max Act: 1.0825. Min Act: -0.0000

Data Index: 510805 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1141172 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.9009. Min Act: -0.0000

Data Index: 411341 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7773. Min Act: -0.0000

Data Index: 875579 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7968. Min Act: -0.0000

Data Index: 453057 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.8465. Min Act: -0.0000

Data Index: 592954 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1033320 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.8261. Min Act: -0.0000

Data Index: 893360 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7188. Min Act: -0.0000

Data Index: 732007 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7475. Min Act: -0.0000

Data Index: 903869 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7270. Min Act: -0.0000

Data Index: 316511 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1303338 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.7082. Min Act: -0.0000

Data Index: 231329 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6605. Min Act: -0.0000

Data Index: 864258 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6249. Min Act: -0.0000

Data Index: 435922 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6411. Min Act: -0.0000

Data Index: 929597 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6377. Min Act: -0.0000

Data Index: 801337 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6346. Min Act: -0.0000

Data Index: 906429 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6773. Min Act: -0.0000

Data Index: 810696 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 1.0825. Min Range: -1.0825

Max Act: 0.6903. Min Act: -0.0000

Data Index: 54670 (C4 (Web Text))

Max Activating Token Index: 709