Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 251 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.1591. Min Act: -0.1700

Data Index: 503672 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.1302. Min Act: -0.1700

Data Index: 835522 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.1230. Min Act: -0.1699

Data Index: 266270 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0728. Min Act: -0.1700

Data Index: 553924 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0721. Min Act: -0.1699

Data Index: 305136 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0603. Min Act: -0.1700

Data Index: 726274 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0387. Min Act: -0.1700

Data Index: 613905 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0437. Min Act: -0.1700

Data Index: 366293 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0531. Min Act: -0.1700

Data Index: 953214 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0169. Min Act: -0.1700

Data Index: 868514 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0228. Min Act: -0.1700

Data Index: 873810 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0175. Min Act: -0.1700

Data Index: 49381 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.1591. Min Range: -3.1591

Max Act: 3.0240. Min Act: -0.1700

Data Index: 1258338 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.9995. Min Act: -0.1700

Data Index: 411609 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.9882. Min Act: -0.1700

Data Index: 983590 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.9876. Min Act: -0.1700

Data Index: 493279 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.9676. Min Act: -0.1700

Data Index: 275581 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.9659. Min Act: -0.1700

Data Index: 1288024 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.9846. Min Act: -0.1700

Data Index: 817554 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 3.1591. Min Range: -3.1591

Max Act: 2.9753. Min Act: -0.1700

Data Index: 902098 (C4 (Web Text))

Max Activating Token Index: 764