Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1613 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6984. Min Act: -0.1700

Data Index: 19833 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6671. Min Act: -0.1700

Data Index: 1119437 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6671. Min Act: -0.1700

Data Index: 771934 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6514. Min Act: -0.1700

Data Index: 948812 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6514. Min Act: -0.1700

Data Index: 1274557 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6514. Min Act: -0.1700

Data Index: 1037321 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6514. Min Act: -0.1700

Data Index: 615380 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6358. Min Act: -0.1700

Data Index: 394911 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6044. Min Act: -0.1700

Data Index: 36226 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6358. Min Act: -0.1700

Data Index: 1049848 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6358. Min Act: -0.1700

Data Index: 80402 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6358. Min Act: -0.1700

Data Index: 418431 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6358. Min Act: -0.1700

Data Index: 1283432 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6358. Min Act: -0.1700

Data Index: 175815 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6044. Min Act: -0.1700

Data Index: 1329928 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6201. Min Act: -0.1700

Data Index: 20064 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6201. Min Act: -0.1700

Data Index: 810598 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1063815 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6044. Min Act: -0.1700

Data Index: 913128 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 3.6984. Min Range: -3.6984

Max Act: 3.6358. Min Act: -0.1700

Data Index: 381393 (C4 (Web Text))

Max Activating Token Index: 503