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

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

Neuron 5056 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0295. Min Range: -1.0295

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1509018 (Python Code)

Max Activating Token Index: 692

Text #1

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1382173 (Python Code)

Max Activating Token Index: 770

Text #2

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1362571 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1439736 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1589539 (Python Code)

Max Activating Token Index: 219

Text #5

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.8653. Min Act: -0.0000

Data Index: 226898 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1514234 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1473077 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1605225 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7507. Min Act: -0.0000

Data Index: 138384 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1542204 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1397537 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1522357 (Python Code)

Max Activating Token Index: 130

Text #13

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1591937 (Python Code)

Max Activating Token Index: 289

Text #14

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7630. Min Act: -0.0000

Data Index: 620467 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1448851 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1409829 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1546283 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1416694 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 1.0295. Min Range: -1.0295

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1546657 (Python Code)

Max Activating Token Index: 493