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

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

Neuron 1325 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.8991. Min Act: -0.1700

Data Index: 232243 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.8052. Min Act: -0.1700

Data Index: 329985 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.6801. Min Act: -0.1700

Data Index: 1344996 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.6801. Min Act: -0.1700

Data Index: 917180 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.6488. Min Act: -0.1700

Data Index: 525814 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.6175. Min Act: -0.1700

Data Index: 790023 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.6488. Min Act: -0.1700

Data Index: 147023 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.6175. Min Act: -0.1700

Data Index: 784144 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.6175. Min Act: -0.1700

Data Index: 777404 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.6175. Min Act: -0.1700

Data Index: 889420 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5862. Min Act: -0.1700

Data Index: 261562 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5862. Min Act: -0.1700

Data Index: 1151162 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5862. Min Act: -0.1700

Data Index: 1311357 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5862. Min Act: -0.1700

Data Index: 1191712 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5862. Min Act: -0.1700

Data Index: 849166 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5548. Min Act: -0.1700

Data Index: 458782 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5548. Min Act: -0.1700

Data Index: 908504 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5548. Min Act: -0.1700

Data Index: 478742 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5235. Min Act: -0.1700

Data Index: 908507 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 3.8991. Min Range: -3.8991

Max Act: 3.5548. Min Act: -0.1700

Data Index: 404928 (C4 (Web Text))

Max Activating Token Index: 17