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

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

Neuron 871 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.4017. Min Act: -0.0000

Data Index: 1264316 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.3748. Min Act: -0.0000

Data Index: 1368978 (Python Code)

Max Activating Token Index: 400

Text #2

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.3407. Min Act: -0.0000

Data Index: 1488944 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.4595. Min Act: -0.0000

Data Index: 1388385 (Python Code)

Max Activating Token Index: 485

Text #4

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.2448. Min Act: -0.0000

Data Index: 761291 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.3240. Min Act: -0.0000

Data Index: 1525400 (Python Code)

Max Activating Token Index: 537

Text #6

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.2291. Min Act: -0.0000

Data Index: 1497824 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.1146. Min Act: -0.0000

Data Index: 1430150 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.2176. Min Act: -0.0000

Data Index: 1650556 (Python Code)

Max Activating Token Index: 812

Text #9

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.2011. Min Act: -0.0000

Data Index: 773355 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.1789. Min Act: -0.0000

Data Index: 198142 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.2848. Min Act: -0.0000

Data Index: 1581868 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.1663. Min Act: -0.0000

Data Index: 1520397 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.0959. Min Act: -0.0000

Data Index: 46497 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.0863. Min Act: -0.0000

Data Index: 1573702 (Python Code)

Max Activating Token Index: 626

Text #15

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.1206. Min Act: -0.0000

Data Index: 1181768 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 2.4595. Min Range: -2.4595

Max Act: 1.9140. Min Act: -0.0000

Data Index: 697629 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.1302. Min Act: -0.0000

Data Index: 1465035 (Python Code)

Max Activating Token Index: 251

Text #18

Max Range: 2.4595. Min Range: -2.4595

Max Act: 2.0242. Min Act: -0.0000

Data Index: 1643878 (Python Code)

Max Activating Token Index: 325

Text #19

Max Range: 2.4595. Min Range: -2.4595

Max Act: 1.9944. Min Act: -0.0000

Data Index: 1061903 (C4 (Web Text))

Max Activating Token Index: 365