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

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

Neuron 413 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.5931. Min Act: -0.0000

Data Index: 1517344 (Python Code)

Max Activating Token Index: 265

Text #1

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1429610 (Python Code)

Max Activating Token Index: 718

Text #2

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.4874. Min Act: -0.0000

Data Index: 1387597 (Python Code)

Max Activating Token Index: 291

Text #3

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.4762. Min Act: -0.0000

Data Index: 1438191 (Python Code)

Max Activating Token Index: 277

Text #4

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1426194 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.2227. Min Act: -0.0000

Data Index: 1490494 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1388104 (Python Code)

Max Activating Token Index: 240

Text #7

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1506244 (Python Code)

Max Activating Token Index: 445

Text #8

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.2778. Min Act: -0.0000

Data Index: 1528694 (Python Code)

Max Activating Token Index: 837

Text #9

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1531055 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.4113. Min Act: -0.0000

Data Index: 1593349 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1507738 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.1872. Min Act: 0.0000

Data Index: 1371094 (Python Code)

Max Activating Token Index: 539

Text #13

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1419866 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1426396 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1456581 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.0233. Min Act: -0.0000

Data Index: 1364315 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 1.5931. Min Range: -1.5931

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1512294 (Python Code)

Max Activating Token Index: 221

Text #18

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1644865 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 1.5931. Min Range: -1.5931

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1444374 (Python Code)

Max Activating Token Index: 516