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

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

Neuron 4707 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1540. Min Act: -0.0000

Data Index: 276070 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1140798 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1530. Min Act: -0.0000

Data Index: 725806 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.1497. Min Act: -0.0000

Data Index: 663062 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0688. Min Act: -0.0000

Data Index: 957593 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0568. Min Act: -0.0000

Data Index: 139018 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0562. Min Act: -0.0000

Data Index: 433431 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9369. Min Act: -0.0000

Data Index: 350920 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.2143. Min Range: -1.2143

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1064290 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9503. Min Act: -0.0000

Data Index: 49713 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9654. Min Act: -0.0000

Data Index: 40572 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9274. Min Act: -0.0000

Data Index: 667484 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9423. Min Act: -0.0000

Data Index: 560302 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9362. Min Act: -0.0000

Data Index: 895789 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9113. Min Act: -0.0000

Data Index: 953037 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9228. Min Act: -0.0000

Data Index: 588964 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.9285. Min Act: -0.0000

Data Index: 572384 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8914. Min Act: -0.0000

Data Index: 991362 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8885. Min Act: -0.0000

Data Index: 632648 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 1.2143. Min Range: -1.2143

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1334965 (C4 (Web Text))

Max Activating Token Index: 790