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

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

Neuron 1733 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: 3.6733. Min Range: -3.6733

Max Act: 3.6733. Min Act: -0.1700

Data Index: 932972 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.5029. Min Act: -0.1700

Data Index: 1328021 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.4409. Min Act: -0.1700

Data Index: 1298260 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.4020. Min Act: -0.1700

Data Index: 1343614 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.4050. Min Act: -0.1700

Data Index: 1254772 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.3979. Min Act: -0.1700

Data Index: 1302328 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.3719. Min Act: -0.1700

Data Index: 716749 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.3400. Min Act: -0.1700

Data Index: 562692 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.3319. Min Act: -0.1700

Data Index: 11014 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.3155. Min Act: -0.1700

Data Index: 705596 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.3184. Min Act: -0.1700

Data Index: 840942 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.3253. Min Act: -0.1700

Data Index: 924471 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.2996. Min Act: -0.1700

Data Index: 1235977 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.2942. Min Act: -0.1700

Data Index: 961241 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.2900. Min Act: -0.1700

Data Index: 334448 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.3107. Min Act: -0.1700

Data Index: 277433 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.2830. Min Act: -0.1700

Data Index: 1509059 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.2827. Min Act: -0.1700

Data Index: 638511 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.2867. Min Act: -0.1697

Data Index: 185394 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 3.6733. Min Range: -3.6733

Max Act: 3.2941. Min Act: -0.1700

Data Index: 498541 (C4 (Web Text))

Max Activating Token Index: 75