Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2981 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.3047. Min Act: -0.0001

Data Index: 27441 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2973. Min Act: -0.0001

Data Index: 1058010 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2990. Min Act: -0.0001

Data Index: 562944 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2682. Min Act: -0.0001

Data Index: 604627 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2647. Min Act: -0.0001

Data Index: 561816 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2727. Min Act: -0.0001

Data Index: 162921 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2522. Min Act: -0.0001

Data Index: 528159 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2521. Min Act: -0.0001

Data Index: 1624881 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2488. Min Act: -0.0001

Data Index: 1398185 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2456. Min Act: -0.0001

Data Index: 974209 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2558. Min Act: -0.0001

Data Index: 1474523 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2547. Min Act: -0.0001

Data Index: 1319608 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2452. Min Act: -0.0001

Data Index: 861214 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2454. Min Act: -0.0001

Data Index: 549725 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1395688 (Python Code)

Max Activating Token Index: 777

Text #15

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2285. Min Act: -0.0001

Data Index: 570638 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2346. Min Act: -0.0001

Data Index: 226258 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2328. Min Act: -0.0001

Data Index: 397116 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2320. Min Act: -0.0001

Data Index: 1655172 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2236. Min Act: -0.0001

Data Index: 219089 (C4 (Web Text))

Max Activating Token Index: 41