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

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

Neuron 2080 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1639251 (Python Code)

Max Activating Token Index: 794

Text #1

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1492332 (Python Code)

Max Activating Token Index: 837

Text #2

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1387508 (Python Code)

Max Activating Token Index: 494

Text #3

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1436027 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1568852 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1401462 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1430901 (Python Code)

Max Activating Token Index: 707

Text #7

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1643367 (Python Code)

Max Activating Token Index: 774

Text #8

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1524864 (Python Code)

Max Activating Token Index: 553

Text #9

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1470091 (Python Code)

Max Activating Token Index: 957

Text #10

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1649554 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1432851 (Python Code)

Max Activating Token Index: 254

Text #12

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1458578 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1553902 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1588093 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1509451 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1371342 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1431029 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1644324 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1426020 (Python Code)

Max Activating Token Index: 316