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

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

Neuron 5703 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4372. Min Range: -2.4372

Max Act: 2.4372. Min Act: -0.0000

Data Index: 1478325 (Python Code)

Max Activating Token Index: 289

Text #1

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.9715. Min Act: -0.0000

Data Index: 1530501 (Python Code)

Max Activating Token Index: 400

Text #2

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.9527. Min Act: -0.0000

Data Index: 1463037 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1540464 (Python Code)

Max Activating Token Index: 802

Text #4

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.9087. Min Act: -0.0000

Data Index: 1411670 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.9073. Min Act: -0.0000

Data Index: 1539224 (Python Code)

Max Activating Token Index: 483

Text #6

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.7819. Min Act: -0.0000

Data Index: 1602106 (Python Code)

Max Activating Token Index: 300

Text #7

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.7789. Min Act: -0.0000

Data Index: 1448178 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.8001. Min Act: -0.0000

Data Index: 1478496 (Python Code)

Max Activating Token Index: 410

Text #9

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.8719. Min Act: -0.0000

Data Index: 1651677 (Python Code)

Max Activating Token Index: 745

Text #10

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.9496. Min Act: -0.0000

Data Index: 1410311 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1545843 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.8141. Min Act: -0.0000

Data Index: 1601277 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.9038. Min Act: -0.0000

Data Index: 1563523 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.8833. Min Act: -0.0000

Data Index: 1606988 (Python Code)

Max Activating Token Index: 580

Text #15

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.7772. Min Act: -0.0000

Data Index: 1426155 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1638312 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.7378. Min Act: -0.0000

Data Index: 1498779 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.9389. Min Act: -0.0000

Data Index: 1448745 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 2.4372. Min Range: -2.4372

Max Act: 1.8068. Min Act: -0.0000

Data Index: 1621333 (Python Code)

Max Activating Token Index: 193