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

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

Neuron 1894 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.3045. Min Act: -0.1700

Data Index: 1188118 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.2731. Min Act: -0.1700

Data Index: 1066409 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.2574. Min Act: -0.1700

Data Index: 145841 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.2259. Min Act: -0.1700

Data Index: 196770 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.2259. Min Act: -0.1700

Data Index: 432274 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.2416. Min Act: -0.1700

Data Index: 563616 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.2259. Min Act: -0.1700

Data Index: 841613 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1945. Min Act: -0.1700

Data Index: 1312538 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1945. Min Act: -0.1700

Data Index: 849015 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1945. Min Act: -0.1700

Data Index: 508621 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1787. Min Act: -0.1700

Data Index: 384788 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1787. Min Act: -0.1700

Data Index: 1073798 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1787. Min Act: -0.1700

Data Index: 207693 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1787. Min Act: -0.1700

Data Index: 909828 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1787. Min Act: -0.1700

Data Index: 880755 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1630. Min Act: -0.1700

Data Index: 1018884 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1157. Min Act: -0.1700

Data Index: 776162 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1315. Min Act: -0.1700

Data Index: 962714 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1472. Min Act: -0.1700

Data Index: 756755 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 3.3045. Min Range: -3.3045

Max Act: 3.1472. Min Act: -0.1700

Data Index: 1145988 (C4 (Web Text))

Max Activating Token Index: 18