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

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

Neuron 679 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.1670. Min Act: -0.0000

Data Index: 1420885 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 3.1670. Min Range: -3.1670

Max Act: 2.9220. Min Act: 0.0000

Data Index: 1436941 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 3.1670. Min Range: -3.1670

Max Act: 2.2890. Min Act: -0.0000

Data Index: 1365470 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 3.1670. Min Range: -3.1670

Max Act: 2.2176. Min Act: -0.0000

Data Index: 1419054 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 3.1670. Min Range: -3.1670

Max Act: 2.0347. Min Act: -0.0000

Data Index: 1597256 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1385634 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.8819. Min Act: 0.0001

Data Index: 1511255 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1538726 (Python Code)

Max Activating Token Index: 120

Text #8

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.8397. Min Act: 0.0001

Data Index: 1504382 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.6636. Min Act: 0.0001

Data Index: 1581385 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.7136. Min Act: -0.0000

Data Index: 1412730 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.6560. Min Act: 0.0000

Data Index: 1481750 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.6212. Min Act: -0.0000

Data Index: 1486831 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.7279. Min Act: -0.0000

Data Index: 1381939 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.5179. Min Act: -0.0000

Data Index: 1503808 (Python Code)

Max Activating Token Index: 163

Text #15

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1458189 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.5471. Min Act: -0.0000

Data Index: 1591049 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.6419. Min Act: -0.0000

Data Index: 1574198 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.5282. Min Act: 0.0000

Data Index: 1587550 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 3.1670. Min Range: -3.1670

Max Act: 1.5239. Min Act: -0.0000

Data Index: 1560050 (Python Code)

Max Activating Token Index: 235