Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 241 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0921. Min Range: -5.0921

Max Act: 5.0921. Min Act: -0.1700

Data Index: 1611913 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.9046. Min Act: -0.1700

Data Index: 226366 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.7796. Min Act: -0.1700

Data Index: 1398419 (Python Code)

Max Activating Token Index: 761

Text #3

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.7484. Min Act: -0.1700

Data Index: 1499596 (Python Code)

Max Activating Token Index: 676

Text #4

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.5921. Min Act: -0.1693

Data Index: 1357798 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.5609. Min Act: -0.1700

Data Index: 77607 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.5296. Min Act: -0.1700

Data Index: 643864 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.4671. Min Act: -0.1700

Data Index: 557893 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.4359. Min Act: -0.1700

Data Index: 851433 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.4359. Min Act: -0.1700

Data Index: 100751 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3734. Min Act: -0.1700

Data Index: 1235756 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.4046. Min Act: -0.1700

Data Index: 1095157 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3734. Min Act: -0.1700

Data Index: 581127 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3421. Min Act: -0.1700

Data Index: 282044 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3734. Min Act: -0.1700

Data Index: 662399 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3734. Min Act: -0.1700

Data Index: 968762 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3734. Min Act: -0.1700

Data Index: 1154955 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3421. Min Act: -0.1700

Data Index: 986366 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3421. Min Act: -0.1700

Data Index: 731413 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 5.0921. Min Range: -5.0921

Max Act: 4.3421. Min Act: -0.1700

Data Index: 543693 (C4 (Web Text))

Max Activating Token Index: 139