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

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

Neuron 4985 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1585720 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1404768 (Python Code)

Max Activating Token Index: 524

Text #2

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1540035 (Python Code)

Max Activating Token Index: 308

Text #3

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1458453 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1364745 (Python Code)

Max Activating Token Index: 1009

Text #5

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1600360 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1425791 (Python Code)

Max Activating Token Index: 234

Text #7

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1389272 (Python Code)

Max Activating Token Index: 75

Text #8

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1114074 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1618071 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7845. Min Act: -0.0000

Data Index: 665264 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1601521 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1376669 (Python Code)

Max Activating Token Index: 382

Text #13

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1593015 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1506033 (Python Code)

Max Activating Token Index: 213

Text #15

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1570825 (Python Code)

Max Activating Token Index: 274

Text #16

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1506589 (Python Code)

Max Activating Token Index: 907

Text #17

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1544334 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1412492 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 0.8428. Min Range: -0.8428

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1480528 (Python Code)

Max Activating Token Index: 1007