Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 171 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.4000. Min Act: -0.0001

Data Index: 887431 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2876. Min Act: -0.0001

Data Index: 1384468 (Python Code)

Max Activating Token Index: 591

Text #2

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1172912 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2554. Min Act: -0.0001

Data Index: 420289 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2817. Min Act: -0.0001

Data Index: 1483677 (Python Code)

Max Activating Token Index: 205

Text #5

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1568162 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2752. Min Act: -0.0001

Data Index: 691800 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2541. Min Act: -0.0001

Data Index: 822468 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2109. Min Act: -0.0001

Data Index: 475554 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1213604 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2395. Min Act: -0.0001

Data Index: 361327 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1405578 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2343. Min Act: -0.0001

Data Index: 1405390 (Python Code)

Max Activating Token Index: 117

Text #13

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2322. Min Act: -0.0001

Data Index: 741179 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2304. Min Act: -0.0001

Data Index: 881471 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2294. Min Act: -0.0001

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2142. Min Act: -0.0001

Data Index: 632987 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2227. Min Act: -0.0001

Data Index: 97618 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1398586 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 0.4000. Min Range: -0.4000

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1560942 (Python Code)

Max Activating Token Index: 291