Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4888. Min Range: -1.4888

Max Act: 1.4888. Min Act: -0.0000

Data Index: 379063 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 1.4888. Min Range: -1.4888

Max Act: 1.0967. Min Act: -0.0000

Data Index: 1154468 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.6209. Min Act: -0.0000

Data Index: 17092 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.7054. Min Act: -0.0000

Data Index: 956136 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.6370. Min Act: -0.0000

Data Index: 564438 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1002839 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.5650. Min Act: -0.0000

Data Index: 364050 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.5953. Min Act: -0.0000

Data Index: 155570 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.5131. Min Act: -0.0000

Data Index: 219755 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.5140. Min Act: -0.0000

Data Index: 786254 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.5012. Min Act: -0.0000

Data Index: 148 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.4963. Min Act: -0.0000

Data Index: 810538 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1350434 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.4977. Min Act: -0.0000

Data Index: 443952 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.4603. Min Act: -0.0000

Data Index: 589522 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.4844. Min Act: -0.0000

Data Index: 60314 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1145964 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.4505. Min Act: -0.0000

Data Index: 390416 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1271850 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.4888. Min Range: -1.4888

Max Act: 0.4418. Min Act: -0.0000

Data Index: 419665 (C4 (Web Text))

Max Activating Token Index: 87