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

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

Neuron 1444 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: 3.6685. Min Range: -3.6685

Max Act: 3.6685. Min Act: -0.1700

Data Index: 699080 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.4649. Min Act: -0.1700

Data Index: 879727 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.3551. Min Act: -0.1700

Data Index: 341124 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.3237. Min Act: -0.1700

Data Index: 411346 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2766. Min Act: -0.1700

Data Index: 745983 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2451. Min Act: -0.1700

Data Index: 540603 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.3080. Min Act: -0.1700

Data Index: 15030 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2451. Min Act: -0.1700

Data Index: 432530 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2766. Min Act: -0.1700

Data Index: 386537 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2451. Min Act: -0.1700

Data Index: 888316 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2294. Min Act: -0.1700

Data Index: 211763 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2294. Min Act: -0.1700

Data Index: 600262 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2451. Min Act: -0.1700

Data Index: 690580 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2294. Min Act: -0.1700

Data Index: 1320676 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2451. Min Act: -0.1700

Data Index: 1138143 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2294. Min Act: -0.1700

Data Index: 1065257 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2137. Min Act: -0.1700

Data Index: 819933 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2137. Min Act: -0.1700

Data Index: 1354785 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2137. Min Act: -0.1700

Data Index: 289997 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.6685. Min Range: -3.6685

Max Act: 3.2137. Min Act: -0.1700

Data Index: 1052088 (C4 (Web Text))

Max Activating Token Index: 224