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

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

Neuron 1108 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: 3.1974. Min Range: -3.1974

Max Act: 3.1974. Min Act: -0.1700

Data Index: 20978 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1502. Min Act: -0.1700

Data Index: 169424 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1345. Min Act: -0.1700

Data Index: 592667 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1307620 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1174333 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1187. Min Act: -0.1700

Data Index: 1090308 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1502. Min Act: -0.1700

Data Index: 1001646 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1328594 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1187. Min Act: -0.1700

Data Index: 1296563 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1187. Min Act: -0.1700

Data Index: 685715 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.0872. Min Act: -0.1700

Data Index: 3519 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1187. Min Act: -0.1700

Data Index: 1026459 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.0872. Min Act: -0.1700

Data Index: 238356 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1030. Min Act: -0.1700

Data Index: 937026 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1030. Min Act: -0.1700

Data Index: 103537 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.0872. Min Act: -0.1700

Data Index: 491620 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1030. Min Act: -0.1700

Data Index: 1122779 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1030. Min Act: -0.1700

Data Index: 661291 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1187. Min Act: -0.1700

Data Index: 371864 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 3.1974. Min Range: -3.1974

Max Act: 3.1030. Min Act: -0.1700

Data Index: 1293178 (C4 (Web Text))

Max Activating Token Index: 691