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

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

Neuron 1912 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: 3.2557. Min Range: -3.2557

Max Act: 3.2557. Min Act: -0.1700

Data Index: 132434 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2557. Min Act: -0.1700

Data Index: 1293560 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2399. Min Act: -0.1700

Data Index: 137940 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2399. Min Act: -0.1700

Data Index: 1269552 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2085. Min Act: -0.1700

Data Index: 292909 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2085. Min Act: -0.1700

Data Index: 211951 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2085. Min Act: -0.1700

Data Index: 1046065 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2085. Min Act: -0.1700

Data Index: 264224 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1928. Min Act: -0.1700

Data Index: 506122 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.2085. Min Act: -0.1700

Data Index: 1258083 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1928. Min Act: -0.1700

Data Index: 460808 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1770. Min Act: -0.1700

Data Index: 85942 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1770. Min Act: -0.1700

Data Index: 304553 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1770. Min Act: -0.1700

Data Index: 1259034 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1770. Min Act: -0.1700

Data Index: 1183590 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1770. Min Act: -0.1700

Data Index: 1301553 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1770. Min Act: -0.1700

Data Index: 429241 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1455. Min Act: -0.1700

Data Index: 794405 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1140. Min Act: -0.1700

Data Index: 127316 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 3.2557. Min Range: -3.2557

Max Act: 3.1140. Min Act: -0.1700

Data Index: 249593 (C4 (Web Text))

Max Activating Token Index: 729