Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 660 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.3299. Min Act: -0.1700

Data Index: 991553 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.3299. Min Act: -0.1700

Data Index: 1036039 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2827. Min Act: -0.1700

Data Index: 1173576 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2513. Min Act: -0.1700

Data Index: 1077756 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2513. Min Act: -0.1700

Data Index: 785347 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1005908 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2670. Min Act: -0.1700

Data Index: 511038 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2199. Min Act: -0.1700

Data Index: 156280 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2513. Min Act: -0.1700

Data Index: 1340724 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2199. Min Act: -0.1700

Data Index: 940596 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2041. Min Act: -0.1700

Data Index: 1032544 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2041. Min Act: -0.1700

Data Index: 1133281 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2199. Min Act: -0.1700

Data Index: 353163 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2513. Min Act: -0.1700

Data Index: 1258295 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2041. Min Act: -0.1700

Data Index: 1029338 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2041. Min Act: -0.1700

Data Index: 967098 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2041. Min Act: -0.1700

Data Index: 392373 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.1727. Min Act: -0.1700

Data Index: 1282828 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2199. Min Act: -0.1700

Data Index: 132946 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 3.3299. Min Range: -3.3299

Max Act: 3.2041. Min Act: -0.1700

Data Index: 487788 (C4 (Web Text))

Max Activating Token Index: 98