Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2662 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.6078. Min Act: -0.0001

Data Index: 24259 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.2377. Min Act: -0.0001

Data Index: 463863 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.6589. Min Act: -0.0001

Data Index: 1202608 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.7805. Min Act: -0.0001

Data Index: 453673 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.5349. Min Act: -0.0001

Data Index: 1261041 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.6573. Min Act: -0.0001

Data Index: 1151319 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.3191. Min Act: -0.0001

Data Index: 455104 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.3265. Min Act: -0.0001

Data Index: 499746 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.4413. Min Act: -0.0001

Data Index: 366636 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.2570. Min Act: -0.0001

Data Index: 579847 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.3859. Min Act: -0.0001

Data Index: 1195582 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.9586. Min Act: -0.0001

Data Index: 1249594 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.1932. Min Act: -0.0001

Data Index: 1293757 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.3497. Min Act: -0.0001

Data Index: 87123 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.4718. Min Act: -0.0001

Data Index: 860640 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.4513. Min Act: -0.0001

Data Index: 575298 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.1561. Min Act: -0.0001

Data Index: 1324363 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.4421. Min Act: -0.0001

Data Index: 89048 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.2710. Min Act: -0.0001

Data Index: 1196389 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 3.9586. Min Range: -3.9586

Max Act: 3.2600. Min Act: -0.0001

Data Index: 236143 (C4 (Web Text))

Max Activating Token Index: 258