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

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

Neuron 4178 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: 1.4543. Min Range: -1.4543

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1576852 (Python Code)

Max Activating Token Index: 434

Text #1

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1133119 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1584915 (Python Code)

Max Activating Token Index: 1015

Text #3

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1516619 (Python Code)

Max Activating Token Index: 586

Text #4

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1413589 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1514242 (Python Code)

Max Activating Token Index: 394

Text #6

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.3368. Min Act: -0.0000

Data Index: 156671 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.1612. Min Act: -0.0000

Data Index: 185521 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1515051 (Python Code)

Max Activating Token Index: 943

Text #9

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2588. Min Act: -0.0000

Data Index: 1394179 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2413. Min Act: -0.0000

Data Index: 102431 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2136. Min Act: -0.0000

Data Index: 2704 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1012324 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2377. Min Act: -0.0000

Data Index: 848803 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2341. Min Act: -0.0000

Data Index: 789585 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.1979. Min Act: -0.0000

Data Index: 1366519 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2083. Min Act: -0.0000

Data Index: 781021 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2191. Min Act: -0.0000

Data Index: 808018 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2004. Min Act: -0.0000

Data Index: 863055 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 1.4543. Min Range: -1.4543

Max Act: 1.2139. Min Act: -0.0000

Data Index: 1503297 (Python Code)

Max Activating Token Index: 624