Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1639 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.7492. Min Act: -0.1700

Data Index: 1130477 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.7180. Min Act: -0.1700

Data Index: 466447 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.6397. Min Act: -0.1700

Data Index: 69926 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.5458. Min Act: -0.1700

Data Index: 378410 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.5614. Min Act: -0.1700

Data Index: 708099 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.5144. Min Act: -0.1700

Data Index: 718241 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4674. Min Act: -0.1700

Data Index: 1359359 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.5301. Min Act: -0.1700

Data Index: 1096630 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4674. Min Act: -0.1700

Data Index: 233919 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4674. Min Act: -0.1700

Data Index: 671240 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4831. Min Act: -0.1700

Data Index: 439937 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.3890. Min Act: -0.1700

Data Index: 358965 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4361. Min Act: -0.1700

Data Index: 1322109 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4674. Min Act: -0.1700

Data Index: 443165 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4674. Min Act: -0.1700

Data Index: 51037 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4204. Min Act: -0.1700

Data Index: 555503 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4204. Min Act: -0.1700

Data Index: 534857 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.3890. Min Act: -0.1700

Data Index: 451218 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4361. Min Act: -0.1700

Data Index: 591950 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 3.7492. Min Range: -3.7492

Max Act: 3.4047. Min Act: -0.1700

Data Index: 57198 (C4 (Web Text))

Max Activating Token Index: 173