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

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

Neuron 4996 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1927. Min Act: -0.0001

Data Index: 958611 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1202733 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1502. Min Act: -0.0001

Data Index: 844464 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1318. Min Act: -0.0001

Data Index: 376647 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1319927 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1309. Min Act: -0.0001

Data Index: 404175 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1499. Min Act: -0.0001

Data Index: 504579 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1533. Min Act: -0.0001

Data Index: 609394 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1219. Min Act: -0.0001

Data Index: 871475 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1324873 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1435. Min Act: -0.0001

Data Index: 947156 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1388. Min Act: -0.0001

Data Index: 854278 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1184770 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1410. Min Act: -0.0001

Data Index: 722043 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1394. Min Act: -0.0001

Data Index: 557419 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1485. Min Act: -0.0001

Data Index: 546177 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1354. Min Act: -0.0001

Data Index: 392665 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1416. Min Act: -0.0001

Data Index: 925299 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1243. Min Act: -0.0001

Data Index: 535786 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1142782 (C4 (Web Text))

Max Activating Token Index: 39