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

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

Neuron 577 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2150. Min Range: -2.2150

Max Act: 2.1596. Min Act: -0.0001

Data Index: 448969 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 2.2150. Min Range: -2.2150

Max Act: 2.2150. Min Act: -0.0000

Data Index: 99174 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 2.2150. Min Range: -2.2150

Max Act: 2.2036. Min Act: -0.0000

Data Index: 531772 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 2.2150. Min Range: -2.2150

Max Act: 2.0683. Min Act: -0.0000

Data Index: 1119022 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.9820. Min Act: -0.0001

Data Index: 238075 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.9587. Min Act: -0.0001

Data Index: 930744 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.8794. Min Act: -0.0000

Data Index: 1323741 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.6302. Min Act: -0.0000

Data Index: 345035 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.7565. Min Act: -0.0001

Data Index: 536988 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.6907. Min Act: -0.0000

Data Index: 894706 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.7407. Min Act: -0.0001

Data Index: 1016328 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.7321. Min Act: -0.0000

Data Index: 673054 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.7967. Min Act: -0.0000

Data Index: 1152538 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.4792. Min Act: -0.0000

Data Index: 383098 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.6513. Min Act: -0.0000

Data Index: 1343985 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.5981. Min Act: -0.0000

Data Index: 267820 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.5833. Min Act: -0.0000

Data Index: 327776 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.6784. Min Act: -0.0000

Data Index: 5107 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.4516. Min Act: -0.0001

Data Index: 666817 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 2.2150. Min Range: -2.2150

Max Act: 1.5399. Min Act: -0.0000

Data Index: 1633534 (Python Code)

Max Activating Token Index: 149