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

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

Neuron 3853 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7126. Min Act: -0.0001

Data Index: 1135780 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7259. Min Act: -0.0001

Data Index: 56211 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7713. Min Act: -0.0001

Data Index: 103216 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7967. Min Act: -0.0001

Data Index: 1358437 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7157. Min Act: -0.0001

Data Index: 422006 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7414. Min Act: -0.0001

Data Index: 1310490 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6788. Min Act: -0.0001

Data Index: 293872 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7591. Min Act: -0.0001

Data Index: 934888 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7755. Min Act: -0.0001

Data Index: 361682 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6763. Min Act: -0.0001

Data Index: 871478 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7221. Min Act: -0.0001

Data Index: 111454 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6942. Min Act: -0.0001

Data Index: 441456 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1007580 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1231195 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5930. Min Act: -0.0001

Data Index: 1293537 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6606. Min Act: -0.0001

Data Index: 1305764 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6955. Min Act: -0.0001

Data Index: 790811 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5970. Min Act: -0.0001

Data Index: 1014313 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6570. Min Act: -0.0001

Data Index: 935426 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6986. Min Act: -0.0001

Data Index: 151175 (C4 (Web Text))

Max Activating Token Index: 885