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

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

Neuron 1587 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: 2.8721. Min Range: -2.8721

Max Act: 2.8721. Min Act: -0.1700

Data Index: 690431 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.8547. Min Act: -0.1700

Data Index: 406051 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.8022. Min Act: -0.1700

Data Index: 536887 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.8315. Min Act: -0.1700

Data Index: 75930 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.8112. Min Act: -0.1700

Data Index: 421978 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.8150. Min Act: -0.1700

Data Index: 934318 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7763. Min Act: -0.1700

Data Index: 565651 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7611. Min Act: -0.1700

Data Index: 1018891 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7776. Min Act: -0.1700

Data Index: 1128782 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7825. Min Act: -0.1700

Data Index: 516774 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7911. Min Act: -0.1700

Data Index: 950924 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.8048. Min Act: -0.1700

Data Index: 940954 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7821. Min Act: -0.1700

Data Index: 822510 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7504. Min Act: -0.1700

Data Index: 1581520 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7491. Min Act: -0.1700

Data Index: 291451 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7595. Min Act: -0.1700

Data Index: 536149 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7607. Min Act: -0.1700

Data Index: 1189605 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7815. Min Act: -0.1700

Data Index: 1272574 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7544. Min Act: -0.1700

Data Index: 1148353 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 2.8721. Min Range: -2.8721

Max Act: 2.7714. Min Act: -0.1700

Data Index: 230713 (C4 (Web Text))

Max Activating Token Index: 116