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

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

Neuron 3285 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4431. Min Act: -0.0000

Data Index: 613388 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4388. Min Act: -0.0000

Data Index: 369840 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1303961 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3524. Min Act: -0.0000

Data Index: 844069 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3161. Min Act: -0.0000

Data Index: 519009 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1199520 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1157936 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3427. Min Act: -0.0000

Data Index: 628223 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3066. Min Act: -0.0000

Data Index: 855318 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3069. Min Act: -0.0000

Data Index: 950221 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.2941. Min Act: -0.0000

Data Index: 645191 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1189404 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1381470 (Python Code)

Max Activating Token Index: 963

Text #13

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1539686 (Python Code)

Max Activating Token Index: 761

Text #14

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.2894. Min Act: -0.0000

Data Index: 94456 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.2849. Min Act: -0.0000

Data Index: 426990 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.2934. Min Act: -0.0000

Data Index: 939733 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.2927. Min Act: -0.0000

Data Index: 693067 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.2751. Min Act: -0.0000

Data Index: 970617 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3030. Min Act: -0.0000

Data Index: 370660 (C4 (Web Text))

Max Activating Token Index: 608