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

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

Neuron 1135 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.6514. Min Act: -0.1700

Data Index: 979927 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.6671. Min Act: -0.1700

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.6593. Min Act: -0.1700

Data Index: 145709 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5810. Min Act: -0.1700

Data Index: 416006 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5810. Min Act: -0.1700

Data Index: 452405 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5888. Min Act: -0.1700

Data Index: 861857 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.6280. Min Act: -0.1700

Data Index: 976885 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.6045. Min Act: -0.1700

Data Index: 410597 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.6201. Min Act: -0.1700

Data Index: 658931 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5653. Min Act: -0.1700

Data Index: 566872 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5497. Min Act: -0.1700

Data Index: 1098770 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5653. Min Act: -0.1700

Data Index: 1183650 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5183. Min Act: -0.1700

Data Index: 486920 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5183. Min Act: -0.1700

Data Index: 767664 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5418. Min Act: -0.1700

Data Index: 1073454 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5497. Min Act: -0.1700

Data Index: 889037 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5340. Min Act: -0.1700

Data Index: 10391 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5183. Min Act: -0.1700

Data Index: 100094 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5183. Min Act: -0.1700

Data Index: 74336 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 3.6671. Min Range: -3.6671

Max Act: 3.5183. Min Act: -0.1700

Data Index: 376939 (C4 (Web Text))

Max Activating Token Index: 586